Typically, fair machine learning research focuses on a single decision maker and assumes that the underlying population is stationary. However, many of the critical domains motivating this work are characterized by competitive marketplaces with many decision makers. Realistically, we might expect only a subset of them to adopt any non-compulsory fairness-conscious policy, a situation that political philosophers call partial compliance. This possibility raises important questions: how does partial compliance and the consequent strategic behavior of decision subjects affect (...) the allocation outcomes? If k% of employers were to voluntarily adopt a fairness-promoting intervention, should we expect k% progress (in aggregate) towards the benefits of universal adoption, or will the dynamics of partial compliance wash out the hoped-for benefits? How might adopting a global (versus local) perspective impact the conclusions of an auditor? In this paper, we propose a simple model of an employment market, leveraging simulation as a tool to explore the impact of both interaction effects and incentive effects on outcomes and auditing metrics. Our key findings are that at equilibrium: (1) partial compliance by k% of employers can result in far less than proportional (k%) progress towards the full compliance outcomes; (2) the gap is more severe when fair employers match global (vs local) statistics; (3) choices of local vs global statistics can paint dramatically different pictures of the performance vis-a-vis fairness desiderata of compliant versus non-compliant employers; (4) partial compliance based on local parity measures can induce extreme segregation. Finally, we discuss implications for auditors and insights concerning the design of regulatory frameworks. (shrink)

Prediction-based decisions, which are often made by utilizing the tools of machine learning, influence nearly all facets of modern life. Ethical concerns about this widespread practice have given rise to the field of fair machine learning and a number of fairness measures, mathematically precise definitions of fairness that purport to determine whether a given prediction-based decision system is fair. Following Reuben Binns (2017), we take ‘fairness’ in this context to be a placeholder for a (...) variety of normative egalitarian considerations. We explore a few fairness measures to suss out their egalitarian roots and evaluate them, both as formalizations of egalitarian ideas and as assertions of what fairness demands of predictive systems. We pay special attention to a recent and popular fairness measure, counterfactual fairness, which holds that a prediction about an individual is fair if it is the same in the actual world and any counterfactual world where the individual belongs to a different demographic group (cf. Kusner et al. (2018)). (shrink)

The use of AI algorithms in criminal trials has been the subject of very lively ethical and legal debates recently. While there are concerns over the lack of accuracy and the harmful biases that certain algorithms display, new algorithms seem more promising and might lead to more accurate legal decisions. Algorithms seem especially relevant for bail decisions, because such decisions involve statistical data to which human reasoners struggle to give adequate weight. While getting the right legal outcome is a strong (...) desideratum of criminal trials, advocates of the relational theory of procedural justice give us good reason to think that fairness and perceived fairness of legal procedures have a value that is independent from the outcome. According to this literature, one key aspect of fairness is trustworthiness. In this paper, I argue that using certain algorithms to assist bail decisions could increase three diferent aspects of judges’ trustworthiness: (1) actual trustworthiness, (2) rich trustworthiness, and (3) perceived trustworthiness. (shrink)

What can contemporary machine learning (ML) models do? Given the proliferation of ML models in society, answering this question matters to a variety of stakeholders, both public and private. The evaluation of models' capabilities is rapidly emerging as a key subfield of modern ML, buoyed by regulatory attention and government grants. Despite this, the notion of an ML model possessing a capability has not been interrogated: what are we saying when we say that a model is able to (...) do something? And what sorts of evidence bear upon this question? -/- In this paper, we aim to answer these questions, using the capabilities of large language models (LLMs) as a running example. Drawing on the large philosophical literature on abilities, we develop an account of ML models' capabilities which can be usefully applied to the nascent science of model evaluation. Our core proposal is a conditional analysis of model abilities (CAMA): crudely, a machine learning model has a capability to X just when it would reliably succeed at doing X if it 'tried'. The main contribution of the paper is making this proposal precise in the context of ML, resulting in an operationalisation of CAMA applicable to LLMs. We then put CAMA to work, showing that it can help make sense of various features of ML model evaluation practice, as well as suggest procedures for performing fair inter-model comparisons. (shrink)

The use of counterfactuals for considerations of algorithmic fairness and explainability is gaining prominence within the machine learning community and industry. This paper argues for more caution with the use of counterfactuals when the facts to be considered are social categories such as race or gender. We review a broad body of papers from philosophy and social sciences on social ontology and the semantics of counterfactuals, and we conclude that the counterfactual approach in machine learning fairness (...) and social explainability can require an incoherent theory of what social categories are. Our findings suggest that most often the social categories may not admit counterfactual manipulation, and hence may not appropriately satisfy the demands for evaluating the truth or falsity of counterfactuals. This is important because the wide- spread use of counterfactuals in machine learning can lead to misleading results when applied in high-stakes domains. Accordingly, we argue that even though counterfactuals play an essential part in some causal inferences, their use for questions of algorithmic fairness and social explanations can create more problems than they resolve. Our positive result is a set of tenets about using counterfactuals for fairness and explanations in machine learning. (shrink)

Healthcare professionals decide wisely about personalized medicine, treatment plans, and resource allocation by utilizing big data analytics and machine learning. To guarantee that algorithmic recommendations are impartial and fair, however, ethical issues relating to prejudice and data privacy must be taken into account. Big data analytics and machine learning have a great potential to disrupt healthcare, and as these technologies continue to evolve, new opportunities to reform healthcare and enhance patient outcomes may arise. In order (...) to investigate the patient’s outcomes with empirical evidence, this research was conducted using an online survey to incorporate healthcare professionals, patient’s reviews, and clinical staff. The data were analyzed using SmartPLS 4.0 to predict the structural model. The findings revealed a direct impact as positive influence of using machine learning on healthcare performance and patient outcomes through big data analytics. Moreover, it is evident that this can lead to personalized treatment plans, early interventions, and improved patient outcomes. Additionally, big data analytics can help healthcare providers optimize resource allocation, improve operational efficiency, and reduce costs. The impact of big data analytics on patient outcome and healthcare performance is expected to continue to grow, making it an important area for investment and research. (shrink)

A number of findings in the field of machine learning have given rise to questions about what it means for automated scoring- or decisionmaking systems to be fair. One center of gravity in this discussion is whether such systems ought to satisfy classification parity (which requires parity in accuracy across groups, defined by protected attributes) or calibration (which requires similar predictions to have similar meanings across groups, defined by protected attributes). Central to this discussion are impossibility results, (...) owed to Kleinberg et al. (2016), Chouldechova (2017), and Corbett-Davies et al. (2017), which show that classification parity and calibration are often incompatible. This paper aims to argue that classification parity, calibration, and a newer, interesting measure called counterfactual fairness are unsatisfactory measures of fairness, offer a general diagnosis of the failure of these measures, and sketch an alternative approach to understanding fairness in machine learning. (shrink)

Inspired by recent breakthroughs in predictive modeling, practitioners in both industry and government have turned to machine learning with hopes of operationalizing predictions to drive automated decisions. Unfortunately, many social desiderata concerning consequential decisions, such as justice or fairness, have no natural formulation within a purely predictive framework. In efforts to mitigate these problems, researchers have proposed a variety of metrics for quantifying deviations from various statistical parities that we might expect to observe in a fair world (...) and offered a variety of algorithms in attempts to satisfy subsets of these parities or to trade o the degree to which they are satised against utility. In this paper, we connect this approach to fair machine learning to the literature on ideal and non-ideal methodological approaches in political philosophy. The ideal approach requires positing the principles according to which a just world would operate. In the most straightforward application of ideal theory, one supports a proposed policy by arguing that it closes a discrepancy between the real and the perfectly just world. However, by failing to account for the mechanisms by which our non-ideal world arose, the responsibilities of various decision-makers, and the impacts of proposed policies, naive applications of ideal thinking can lead to misguided interventions. In this paper, we demonstrate a connection between the fair machine learning literature and the ideal approach in political philosophy, and argue that the increasingly apparent shortcomings of proposed fair machine learning algorithms reflect broader troubles faced by the ideal approach. We conclude with a critical discussion of the harms of misguided solutions, a reinterpretation of impossibility results, and directions for future research. (shrink)

Holm (2022) argues that a class of algorithmic fairness measures, that he refers to as the ‘performance parity criteria’, can be understood as applications of John Broome’s Fairness Principle. We argue that the performance parity criteria cannot be read this way. This is because in the relevant context, the Fairness Principle requires the equalization of actual individuals’ individual-level chances of obtaining some good (such as an accurate prediction from a predictive system), but the performance parity criteria do not guarantee any (...) such thing: the measures merely ensure that certain population-level ratios hold. (shrink)

Algorithms can now identify patterns and correlations in the (big) datasets, and predict outcomes based on those identified patterns and correlations with the use of machine learning techniques and big data, decisions can then be made by algorithms themselves in accordance with the predicted outcomes. Yet, algorithms can inherit questionable values from the datasets and acquire biases in the course of (machine) learning, and automated algorithmic decision-making makes it more difficult for people to see algorithms as (...) biased. While researchers have taken the problem of algorithmic bias seriously, but the current discussion on algorithmic fairness tends to conceptualize ‘fairness’ in algorithmic fairness primarily as a technical issue and attempts to implement pre-existing ideas of ‘fairness’ into algorithms. In this paper, I show that such a view of algorithmic fairness as technical issue is unsatisfactory for the type of problem algorithmic fairness presents. Since decisions on fairness measure and the related techniques for algorithms essentially involve choices between competing values, ‘fairness’ in algorithmic fairness should be conceptualized first and foremost as a political issue, and it should be (re)solved by democratic communication. The aim of this paper, therefore, is to explicitly reconceptualize algorithmic fairness as a political question and suggest the current discussion of algorithmic fairness can be strengthened by adopting the accountability for reasonableness framework. (shrink)

Recently, there has been much discussion of ‘fair machine learning’: fairness in data-driven decision-making systems (which are often, though not always, made with assistance from machine learning systems). Notorious impossibility results show that we cannot have everything we want here. Such problems call for careful thinking about the foundations of fair machine learning. Sune Holm has identified one promising way forward, which involves applying John Broome's theory of fairness to the puzzles of (...) fair machine learning. Unfortunately, his application of Broome's theory appears to be fatally flawed. This article attempts to rescue Holm's central insight – namely, that Broome's theory can be useful to the study of fair machine learning – by giving an alternative application of Broome's theory, which involves thinking about fair machine learning in counterfactual (as opposed to merely statistical) terms. (shrink)

The application of machine-learning technologies to medical practice promises to enhance the capabilities of healthcare professionals in the assessment, diagnosis, and treatment, of medical conditions. However, there is growing concern that algorithmic bias may perpetuate or exacerbate existing health inequalities. Hence, it matters that we make precise the different respects in which algorithmic bias can arise in medicine, and also make clear the normative relevance of these different kinds of algorithmic bias for broader questions about justice and fairness (...) in healthcare. In this paper, we provide the building blocks for an account of algorithmic bias and its normative relevance in medicine. (shrink)

This paper focuses on two highly publicized formal trade-offs in the field of responsible artificial intelligence (AI) -- between predictive accuracy and fairness and between predictive accuracy and interpretability. These formal trade-offs are often taken by researchers, practitioners, and policy-makers to directly imply corresponding tensions between underlying values. Thus interpreted, the trade-offs have formed a core focus of normative engagement in AI governance, accompanied by a particular division of labor along disciplinary lines. This paper argues against this prevalent interpretation by (...) drawing attention to three sets of considerations that are critical for bridging the gap between these formal trade-offs and their practical impacts on relevant values. I show how neglecting these considerations can distort our normative deliberations, and result in costly and misaligned interventions and justifications. Taken together, these considerations form a sociotechnical framework that could guide those involved in AI governance to assess how, in many cases, we can and should have higher aspirations than the prevalent interpretation of the trade-offs would suggest. I end by drawing out the normative opportunities and challenges that emerge out of these considerations, and highlighting the imperative of interdisciplinary collaboration in fostering responsible AI. (shrink)

In this research, we focus on the usage of adversarial sampling to test for the fairness in the prediction of deep neural network model across different classes of image in a given dataset. While several framework had been proposed to ensure robustness of machine learning model against adversarial attack, some of which includes adversarial training algorithm. There is still the pitfall that adversarial training algorithm tends to cause disparity in accuracy and robustness among different group. Our research is (...) aimed at using adversarial sampling to test for fairness in the prediction of deep neural network model across different classes or categories of image in a given dataset. We successfully demonstrated a new method of ensuring fairness across various group of input in deep neural network classifier. We trained our neural network model on the original image, and without training our model on the perturbed or attacked image. When we feed the adversarial samplings to our model, it was able to predict the original category/ class of the image the adversarial sample belongs to. We also introduced and used the separation of concern concept from software engineering whereby there is an additional standalone filter layer that filters perturbed image by heavily removing the noise or attack before automatically passing it to the network for classification, we were able to have accuracy of 93.3%. Cifar-10 dataset have ten categories of dataset, and so, in order to account for fairness, we applied our hypothesis across each categories of dataset and were able to get a consistent result and accuracy. (shrink)

There is growing concern that decision-making informed by machine learning (ML) algorithms may unfairly discriminate based on personal demographic attributes, such as race and gender. Scholars have responded by introducing numerous mathematical definitions of fairness to test the algorithm, many of which are in conflict with one another. However, these reductionist representations of fairness often bear little resemblance to real-life fairness considerations, which in practice are highly contextual. Moreover, fairness metrics tend to be implemented in narrow and targeted (...) toolkits that are difficult to integrate into an algorithm’s broader ethical assessment. In this paper, we derive lessons from ethical philosophy and welfare economics as they relate to the contextual factors relevant for fairness. In particular we highlight the debate around acceptability of particular inequalities and the inextricable links between fairness, welfare and autonomy. We propose Key Ethics Indicators (KEIs) as a way towards providing a more holistic understanding of whether or not an algorithm is aligned to the decision-maker’s ethical values. (shrink)

This article examines the complaint that arbitrary algorithmic decisions wrong those whom they affect. It makes three contributions. First, it provides an analysis of what arbitrariness means in this context. Second, it argues that arbitrariness is not of moral concern except when special circumstances apply. However, when the same algorithm or different algorithms based on the same data are used in multiple contexts, a person may be arbitrarily excluded from a broad range of opportunities. The third contribution is to explain (...) why this systemic exclusion is of moral concern and to offer a solution to address it. (shrink)

The increasing application of artificial intelligence (AI) to healthcare raises both hope and ethical concerns. Some advanced machine learning methods provide accurate clinical predictions at the expense of a significant lack of explainability. Alex John London has defended that accuracy is a more important value than explainability in AI medicine. In this article, we locate the trade-off between accurate performance and explainable algorithms in the context of distributive justice. We acknowledge that accuracy is cardinal from outcome-oriented justice because (...) it helps to maximize patients’ benefits and optimizes limited resources. However, we claim that the opaqueness of the algorithmic black box and its absence of explainability threatens core commitments of procedural fairness such as accountability, avoidance of bias, and transparency. To illustrate this, we discuss liver transplantation as a case of critical medical resources in which the lack of explainability in AI-based allocation algorithms is procedurally unfair. Finally, we provide a number of ethical recommendations for when considering the use of unexplainable algorithms in the distribution of health-related resources. (shrink)

Research in ethical AI has made strides in quantitative expression of ethical values such as fairness, transparency, and privacy. Here we contribute to this effort by proposing a new family of metrics called “decisional value scores” (DVS). DVSs are scores assigned to a system based on whether the decisions it makes meet or fail to meet a particular standard (either individually, in total, or as a ratio or average over decisions made). Advantages of DVS include greater discrimination capacity between types (...) of ethically relevant decisions and facilitation of ethical comparisons between decisions and decision-making systems, including across different modalities (for instance: human, machine, or coupled human–machine systems). After clarifying ambiguities in the concept of “decision” itself, including the question of how to individuate the decisions made by a system, we discuss the role and meaning of “decision” in common AI and machine learning approaches such as decision trees, neural networks, SVMs, and unsupervised classifiers. We then show how DVSs may be defined for several ethical values of interest, with an extended discussion of transparency. Finally, we explore how such metrics can be applied to real decision-making systems through two case studies: evaluations of LLMs for transparency; and evaluations of criminal risk assessment tools for utility, rights violations, fairness, and transparency. (shrink)

Does the human mind resemble the machines that can behave like it? Biologically inspired machine-learning systems approach “human-level” accuracy in an astounding variety of domains, and even predict human brain activity—raising the exciting possibility that such systems represent the world like we do. However, even seemingly intelligent machines fail in strange and “unhumanlike” ways, threatening their status as models of our minds. How can we know when human–machine behavioral differences reflect deep disparities in their underlying capacities, vs. (...) when such failures are only superficial or peripheral? This article draws on a foundational insight from cognitive science—the distinction between performance and competence—to encourage “species-fair” comparisons between humans and machines. The performance/competence distinction urges us to consider whether the failure of a system to behave as ideally hypothesized, or the failure of one creature to behave like another, arises not because the system lacks the relevant knowledge or internal capacities (“competence”), but instead because of superficial constraints on demonstrating that knowledge (“performance”). I argue that this distinction has been neglected by research comparing human and machine behavior, and that it should be essential to any such comparison. Focusing on the domain of image classification, I identify three factors contributing to the species-fairness of human–machine comparisons, extracted from recent work that equates such constraints. Species-fair comparisons level the playing field between natural and artificial intelligence, so that we can separate more superficial differences from those that may be deep and enduring. (shrink)

This article analyzes emerging artificial intelligence (AI)-enhanced lie detection systems from ethical and human resource (HR) management perspectives. I show how these AI enhancements transform lie detection, followed with analyses as to how the changes can lead to moral problems. Specifically, I examine how these applications of AI introduce human rights issues of fairness, mental privacy, and bias and outline the implications of these changes for HR management. The changes that AI is making to lie detection are altering the roles (...) of human test administrators and human subjects, adding machine learning-based AI agents to the situation and establishing invasive data collection processes as well as introducing certain biases in results. I project that the potentials for pervasive and continuous lie detection initiatives (“truth machines”) are substantial, displacing human-centered efforts to establish trust and foster integrity in organizations. I argue that if it is possible for HR managers to do so, they should cease using technologically-based lie detection systems entirely and work to foster trust and accountability on a human scale. However, if these AI-enhanced technologies are put into place by organizations by law, agency mandate, or other compulsory measures, care should be taken that the impacts of the technologies on human rights and wellbeing are considered. The article explores how AI can displace the human agent in some aspects of lie detection and credibility assessment scenarios, expanding the prospects for inscrutable, “black box” processes and novel physiological constructs (such as “biomarkers of deceit”) that may increase the potential for such human rights concerns as fairness, mental privacy, and bias. Employee interactions with autonomous lie detection systems rather with than human beings who administer specific tests can reframe organizational processes and rules concerning the assessment of personal honesty and integrity. The dystopian projection of organizational life in which analyses and judgments of the honesty of one’s utterances are made automatically and in conjunction with one’s personal profile provides unsettling prospects for the autonomy of self-representation. (shrink)

Turing’s much debated test has turned 70 and is still fairly controversial. His 1950 paper is seen as a complex and multilayered text, and key questions about it remain largely unanswered. Why did Turing select learning from experience as the best approach to achieve machine intelligence? Why did he spend several years working with chess playing as a task to illustrate and test for machine intelligence only to trade it out for conversational question-answering in 1950? Why did (...) Turing refer to gender imitation in a test for machine intelligence? In this article, I shall address these questions by unveiling social, historical and epistemological roots of the so-called Turing test. I will draw attention to a historical fact that has been only scarcely observed in the secondary literature thus far, namely that Turing’s 1950 test emerged out of a controversy over the cognitive capabilities of digital computers, most notably out of debates with physicist and computer pioneer Douglas Hartree, chemist and philosopher Michael Polanyi, and neurosurgeon Geoffrey Jefferson. Seen in its historical context, Turing’s 1950 paper can be understood as essentially a reply to a series of challenges posed to him by these thinkers arguing against his view that machines can think. Turing did propose gender learning and imitation as one of his various imitation tests for machine intelligence, and I argue here that this was done in response to Jefferson's suggestion that gendered behavior is causally related to the physiology of sex hormones. (shrink)

Many of us assume that all the free editing and sorting of online content we ordinarily rely on is carried out by AI algorithms — not human persons. Yet in fact, that is often not the case. This is because human workers remain cheaper, quicker, and more reliable than AI for performing myriad tasks where the right answer turns on ineffable contextual criteria too subtle for algorithms to yet decode. The output of this work is then used for machine (...) learning purposes to generate algorithms constructed from large data sets containing thousands of correctly coded observations. The fact that ghost workers are treated as consumers distorts the basic logic of the employment relationship, effectively placing the worker-as-consumer in the worst of both worlds, in which they hold the legal rights of neither group. This puts them in a regulatory limbo position in which they have little or no protection, control, or guarantee of return on investment. This is because the platforms that facilitate ghost work have orchestrated a three-way virtual relationship that absolves all parties of responsibility, while placing nearly all the risks and opportunity costs squarely on the shoulders of the workers. As a result, we believe such a work arrangement as it stands, does not uphold basic standards of Rawlsian justice as fairness. (shrink)

Since its emergence in the 1960s, Artifcial Intelligence (AI) has grown to conquer many technology products and their felds of application. Machine learning, as a major part of the current AI solutions, can learn from the data and through experience to reach high performance on various tasks. This growing success of AI algorithms has led to a need for interpretability to understand opaque models such as deep neural networks. Various requirements have been raised from diferent domains, together with (...) numerous tools to debug, justify outcomes, and establish the safety, fairness and reliability of the models. This variety of tasks has led to inconsistencies in the terminology with, for instance, terms such as interpretable, explainable and transparent being often used interchangeably in methodology papers. These words, however, convey diferent meanings and are “weighted" diferently across domains, for example in the technical and social sciences. In this paper, we propose an overarching terminology of interpretability of AI systems that can be referred to by the technical developers as much as by the social sciences community to pursue clarity and efciency in the defnition of regulations for ethical and reliable AI development. We show how our taxonomy and defnition of interpretable AI difer from the ones in previous research and how they apply with high versatility to several domains and use cases, proposing a—highly needed—standard for the communication among interdisciplinary areas of AI. (shrink)

Programming artificial intelligence to make fairness assessments of texts through top-down rules, bottom-up training, or hybrid approaches, has presented the challenge of defining cross-cultural fairness. In this paper a simple method is presented which uses vectors to discover if a verb is unfair or fair. It uses already existing relational social ontologies inherent in Word Embeddings and thus requires no training. The plausibility of the approach rests on two premises. That individuals consider fair acts those that they would (...) be willing to accept if done to themselves. Secondly, that such a construal is ontologically reflected in Word Embeddings, by virtue of their ability to reflect the dimensions of such a perception. These dimensions being: responsibility vs. irresponsibility, gain vs. loss, reward vs. sanction, joy vs. pain, all as a single vector. The paper finds it possible to quantify and qualify a verb as fair or unfair by calculating the cosine similarity of the said verb’s embedding vector against FairVec—which represents the above dimensions. We apply this to Glove and Word2Vec embeddings. Testing on a list of verbs produces an F1 score of 95.7, which is improved to 97.0. Lastly, a demonstration of the method’s applicability to sentence measurement is carried out. (shrink)

As inductive decision-making procedures, the inferences made by machine learning programs are subject to underdetermination by evidence and bear inductive risk. One strategy for overcoming these challenges is guided by a presumption in philosophy of science that inductive inferences can and should be value-free. Applied to machine learning programs, the strategy assumes that the influence of values is restricted to data and decision outcomes, thereby omitting internal value-laden design choice points. In this paper, I apply arguments (...) from feminist philosophy of science to machine learning programs to make the case that the resources required to respond to these inductive challenges render critical aspects of their design constitutively value-laden. I demonstrate these points specifically in the case of recidivism algorithms, arguing that contemporary debates concerning fairness in criminal justice risk-assessment programs are best understood as iterations of traditional arguments from inductive risk and demarcation, and thereby establish the value-laden nature of automated decision-making programs. Finally, in light of these points, I address opportunities for relocating the value-free ideal in machine learning and the limitations that accompany them. (shrink)

Simple idealized models seem to provide more understanding than opaque, complex, and hyper-realistic models. However, an increasing number of scientists are going in the opposite direction by utilizing opaque machine learning models to make predictions and draw inferences, suggesting that scientists are opting for models that have less potential for understanding. Are scientists trading understanding for some other epistemic or pragmatic good when they choose a machine learning model? Or are the assumptions behind why minimal models (...) provide understanding misguided? In this paper, using the case of deep neural networks, I argue that it is not the complexity or black box nature of a model that limits how much understanding the model provides. Instead, it is a lack of scientific and empirical evidence supporting the link that connects a model to the target phenomenon that primarily prohibits understanding. (shrink)

Just as humans can draw conclusions responsibly or irresponsibly, so too can computers. Machine learning systems that have been trained on data sets that include irresponsible judgments are likely to yield irresponsible predictions as outputs. In this paper I focus on a particular kind of inference a computer system might make: identification of the intentions with which a person acted on the basis of photographic evidence. Such inferences are liable to be morally objectionable, because of a way in (...) which they are presumptuous. After elaborating this moral concern, I explore the possibility that carefully procuring the training data for image recognition systems could ensure that the systems avoid the problem. The lesson of this paper extends beyond just the particular case of image recognition systems and the challenge of responsibly identifying a person’s intentions. Reflection on this particular case demonstrates the importance (as well as the difficulty) of evaluating machine learning systems and their training data from the standpoint of moral considerations that are not encompassed by ordinary assessments of predictive accuracy. (shrink)

Machine learning algorithms may radically improve our ability to diagnose and treat disease. For moral, legal, and scientific reasons, it is essential that doctors and patients be able to understand and explain the predictions of these models. Scalable, customisable, and ethical solutions can be achieved by working together with relevant stakeholders, including patients, data scientists, and policy makers.

This study employs machine learning to predict diabetes using a Kaggle dataset with 13 features. Our three-layer model achieves an accuracy of 98.73% and an average error of 0.01%. Feature analysis identifies Age, Gender, Polyuria, Polydipsia, Visual blurring, sudden weight loss, partial paresis, delayed healing, irritability, Muscle stiffness, Alopecia, Genital thrush, Weakness, and Obesity as influential predictors. These findings have clinical significance for early diabetes risk assessment. While our research addresses gaps in the field, further work is needed (...) to enhance model generalizability. (shrink)

The rise of social media has created a new platform for communication and interaction, but it has also facilitated the spread of harmful behaviors such as cyberbullying. Detecting and mitigating cyberbullying on social media platforms is a critical challenge that requires advanced technological solutions. This paper presents a novel approach to cyberbullying detection using a combination of supervised machine learning (ML) and natural language processing (NLP) techniques, enhanced by optimization algorithms. The proposed system is designed to identify and (...) classify cyberbullying behavior in real-time, analyzing textual data from social media posts to detect harmful content. The model is trained on a large dataset of labeled instances of bullying and non-bullying content, using supervised ML algorithms such as Support Vector Machines (SVM), Decision Trees, and Random Forest. NLP techniques, including sentiment analysis, keyword extraction, and text vectorization, are employed to preprocess and transform the data into a format suitable for machine learning. To optimize the performance of the detection model, techniques such as Grid Search, Genetic Algorithms, and Particle Swarm Optimization are used to fine-tune hyperparameters, resulting in improved accuracy and reduced false positives. The system's effectiveness is validated through experiments conducted on various social media platforms, demonstrating its potential to detect cyberbullying with high precision. Future work will focus on enhancing the model's adaptability to emerging slang and evolving language patterns in social media. (shrink)

Visual analytics (VA) combines the strengths of human and machine intelligence to enable the discovery of interesting patterns in challenging datasets. Historically, most attention has been given to developing the machine component—for example, machine learning or the human-computer interface. However, it is also essential to develop the abilities of the analysts themselves, especially at the beginning of their careers. -/- For the past several years, we at the University of British Columbia (UBC)—with the support of The (...) Boeing Company—have experimented with various ways of preparing undergraduate students for VA. Although inspired by the need to prepare students to become visual analysts, the result turned out to be fairly general in scope, applicable to other analytical approaches, as well as more general research. In hindsight, this makes considerable sense. Although the visual component of VA is necessary, it is insufficient; many analytical activities at the human end involve nonvisual skills, such as effective decision-making and the ability to quickly focus on the relevant parts of a problem. -/- The result of this experimentation is a third-year undergraduate course titled Cognitive Systems 303 (COGS 303) that focuses on “VA unplugged”—that is, on developing investigative abilities prior to training on the VA systems themselves. It was felt that if students focused on developing basic analytical habits of thought prior to learning VA systems, these habits would be reinforced by subsequent practice on “live” systems. (shrink)

Current methods of operationalizing concepts of misinformation in machine learning are often problematic given idiosyncrasies in their success conditions compared to other models employed in the natural and social sciences. The intrinsic value-ladenness of misinformation and the dynamic relationship between citizens' and social scientists' concepts of misinformation jointly suggest that both the construct legitimacy and the construct validity of these models needs to be assessed via more democratic criteria than has previously been recognized.

As more objections have been raised against grant peer-review for being costly and time-consuming, the legitimate question arises whether machine learning algorithms could help assess the epistemic efficiency of the proposed projects. As a case study, we investigated whether project efficiency in high energy physics can be algorithmically predicted based on the data from the proposal. To analyze the potential of algorithmic prediction in HEP, we conducted a study on data about the structure and outcomes of HEP experiments (...) with the goal of predicting their efficiency. In the first step, we assessed the project efficiency using Data Envelopment Analysis of 67 experiments conducted in the HEP laboratory Fermilab. In the second step, we employed predictive algorithms to detect which team structures maximize the epistemic performance of an expert group. For this purpose, we used the efficiency scores obtained by DEA and applied predictive algorithms – lasso and ridge linear regression, neural network, and gradient boosted trees – on them. The results of the predictive analyses show moderately high accuracy, indicating that they can be beneficial as one of the steps in grant review. Still, their applicability in practice should be approached with caution. Some of the limitations of the algorithmic approach are the unreliability of citation patterns, unobservable variables that influence scientific success, and the potential predictability of the model. (shrink)

One of the predominant debates in AI Ethics is the worry and necessity to create fair, transparent and accountable algorithms that do not perpetuate current social inequities. I offer a critical analysis of Reuben Binns’s argument in which he suggests using public reason to address the potential bias of the outcomes of machine learning algorithms. In contrast to him, I argue that ultimately what is needed is not public reason per se, but an audit of the implicit (...) moral assumptions of societies within which algorithms are built and applied. Public justification is appealing since it offers us the possibility to align the decision-making outcomes of the algorithm with the core moral values of stakeholders within a constitutional democratic society. My concern is that the common moral principles that form the foundation of public reason are not necessarily neutral, as they still express specific moral ideals and normative standards even if there is moral agreement by society as a whole, or among different stakeholders within society. Appealing to such normative standards may thus still lead to algorithmic outcomes being biased as common moral values may very well still be discriminatory even though they are formed from a consensus, and even if public reason is applied as a kind of filter for potential algorithmic outcomes. Hence, I argue that these implicit moral norms within society that we take as a given in public reasoning, need to be audited from generation to generation in order to effectively mitigate potential algorithmic bias. (shrink)

In this paper, we investigated multiple machine learning classifiers which are, Multinomial Naive Bayes, Support Vector Machine, Decision Tree, K Nearest Neighbors, and Random Forest in a text classification problem. The data we used contains real and fake job posts. We cleaned and pre-processed our data, then we applied TF-IDF for feature extraction. After we implemented the classifiers, we trained and evaluated them. Evaluation metrics used are precision, recall, f-measure, and accuracy. For each classifier, results were summarized (...) and compared with others. (shrink)

Issues of reliability are claiming center-stage in the epistemology of machine learning. This paper unifies different branches in the literature and points to promising research directions, whilst also providing an accessible introduction to key concepts in statistics and machine learning – as far as they are concerned with reliability.

As our epistemic ambitions grow, the common and scientific endeavours are becoming increasingly dependent on Machine Learning (ML). The field rests on a single experimental paradigm, which consists of splitting the available data into a training and testing set and using the latter to measure how well the trained ML model generalises to unseen samples. If the model reaches acceptable accuracy, an a posteriori contract comes into effect between humans and the model, supposedly allowing its deployment to target (...) environments. Yet the latter part of the contract depends on human inductive predictions or generalisations, which infer a uniformity between the trained ML model and the targets. The paper asks how we justify the contract between human and machine learning. It is argued that the justification becomes a pressing issue when we use ML to reach ‘elsewheres’ in space and time or deploy ML models in non-benign environments. The paper argues that the only viable version of the contract can be based on optimality (instead of on reliability which cannot be justified without circularity) and aligns this position with Schurz’s optimality justification. It is shown that when dealing with inaccessible/unstable ground-truths (‘elsewheres’ and non-benign targets), the optimality justification undergoes a slight change, which should reflect critically on our epistemic ambitions. Therefore, the study of ML robustness should involve not only heuristics that lead to acceptable accuracies on testing sets. The justification of human inductive predictions or generalisations about the uniformity between ML models and targets should be included as well. Without it, the assumptions about inductive risk minimisation in ML are not addressed in full. (shrink)

Cloud storage's scalability, accessibility, and affordability have made it essential in the digital age. Data security and privacy remain a major issue due to the large volume of sensitive data kept on cloud services. Traditional encryption is safe but slows data recovery, especially for keyword searches. Secure, fine-grained access control and quick keyword searches over encrypted data are possible using attribute-based keyword search (ABKS). This study examines how ABKS might optimize search efficiency and data security in cloud storage systems. We (...) examine index compression, query processing improvement, and encryption optimization to decrease computational cost and preserve security. (shrink)

This paper provides an analysis of the way in which two foundational principles of medical ethics–the trusted doctor and patient autonomy–can be undermined by the use of machine learning (ML) algorithms and addresses its legal significance. This paper can be a guide to both health care providers and other stakeholders about how to anticipate and in some cases mitigate ethical conflicts caused by the use of ML in healthcare. It can also be read as a road map as (...) to what needs to be done to achieve an acceptable level of explainability in an ML algorithm when it is used in a healthcare context. (shrink)

Objectives: Machine learning (ML) has the potential to facilitate “continual learning” in medicine, in which an ML system continues to evolve in response to exposure to new data over time, even after being deployed in a clinical setting. In this article, we provide a tutorial on the range of ethical issues raised by the use of such “adaptive” ML systems in medicine that have, thus far, been neglected in the literature. -/- Target audience: The target audiences for (...) this tutorial are the developers of ML AI systems, healthcare regulators, the broader medical informatics community, and practicing clinicians. -/- Scope: Discussions of adaptive ML systems to date have overlooked the distinction between 2 sorts of variance that such systems may exhibit—diachronic evolution (change over time) and synchronic variation (difference between cotemporaneous instantiations of the algorithm at different sites)—and underestimated the significance of the latter. We highlight the challenges that diachronic evolution and synchronic variation present for the quality of patient care, informed consent, and equity, and discuss the complex ethical trade-offs involved in the design of such systems. (shrink)

It is crucial to actively detect the risks of transactions in a financial company to improve customer experience and minimize financial loss. In this study, we compare different machine learning algorithms to effectively and efficiently predict the legitimacy of financial transactions. The algorithms used in this study were: MLP Repressor, Random Forest Classifier, Complement NB, MLP Classifier, Gaussian NB, Bernoulli NB, LGBM Classifier, Ada Boost Classifier, K Neighbors Classifier, Logistic Regression, Bagging Classifier, Decision Tree Classifier and Deep (...) class='Hi'>Learning. The dataset was collected from Kaggle depository. It consists of 6362620 rows and 10 columns. The best classifier with unbalanced dataset was the Random Forest Classifier. The Accuracy 99.97%, precession 99.96%, Recall 99.97% and the F1-score 99.96%. However, the best classifier with balanced dataset was the Bagging Classifier. The Accuracy 99.96%, precession 99.95%, Recall 99.98% and the F1-score 99.96%. (shrink)

Whether it would take one decade or several centuries, many agree that it is possible to create a *superintelligence*---an artificial intelligence with a godlike ability to achieve its goals. And many who have reflected carefully on this fact agree that our best hope for a "friendly" superintelligence is to design it to *learn* values like ours, since our values are too complex to program or hardwire explicitly. But the value learning approach to AI safety faces three particularly philosophical puzzles: (...) first, it is unclear how any intelligent system could learn its final values, since to judge one supposedly "final" value against another seems to require a further background standard for judging. Second, it is unclear how to determine the content of a system's values based on its physical or computational structure. Finally, there is the distinctly ethical question of which values we should best aim for the system to learn. I outline a potential answer to these interrelated puzzles, centering on a "miktotelic" proposal for blending a complex, learnable final value out of many simpler ones. (shrink)

Researchers and practitioners are increasingly using machine‐generated synthetic data as a tool for advancing health science and practice, by expanding access to health data while—potentially—mitigating privacy and related ethical concerns around data sharing. While using synthetic data in this way holds promise, we argue that it also raises significant ethical, legal, and policy concerns, including persistent privacy and security problems, accuracy and reliability issues, worries about fairness and bias, and new regulatory challenges. The virtue of synthetic data is often (...) understood to be its detachment from the data subjects whose measurement data is used to generate it. However, we argue that addressing the ethical issues synthetic data raises might require bringing data subjects back into the picture, finding ways that researchers and data subjects can be more meaningfully engaged in the construction and evaluation of datasets and in the creation of institutional safeguards that promote responsible use. (shrink)

This article assesses how autonomy and machine learning impact the existential risk of nuclear war. It situates the problem of cyber security, which proceeds by stealth, within the larger context of nuclear deterrence, which is effective when it functions with transparency and credibility. Cyber vulnerabilities poses new weaknesses to the strategic stability provided by nuclear deterrence. This article offers best practices for the use of computer and information technologies integrated into nuclear weapons systems. Focusing on nuclear command and (...) control, avoiding autonomy and machine learning is recommended as one means to reduce the existential risk of unintended nuclear conflict. (shrink)

This dissertation consists of five chapters, each written as independent research papers that are unified by an overarching concern regarding information privacy and machine learning-based artificial intelligence (AI). This dissertation addresses the issues concerning privacy and AI by responding to the following three main research questions (RQs): RQ1. ‘How does an AI system affect privacy?’; RQ2. ‘How effectively does the General Data Protection Regulation (GDPR) assess and address privacy issues concerning both individuals and groups?’; and RQ3. ‘How can (...) the value of privacy be embedded into systems?’ -/- To respond to the RQs, this dissertation adopts the privacy impact assessment (PIA) as the overall methodology. A PIA encompasses three distinct stages; the first, the analytical stage, concerns the analysis of how AI (particularly focusing on inference as a process that includes inferred information, AI models’ performance, and accessing information uncovered by AI models) impacts privacy. Second, the legal assessment stage concerns whether AI that processes personal information and develops models complies with the GDPR. Finally, the design requirements stage features proposals for design requirements for systems aimed at protecting privacy. Accordingly, this dissertation is structured in three parts, each corresponding to a specific stage of a PIA and responding to one of the RQs. -/- Part I, which addresses the first stage of the PIA, comprises three chapters that altogether respond to RQ1. Chapter 2 analyses how AI impacts the descriptive aspect of privacy; this part argues that AI challenges the current definitions of privacy and that the ‘source control’ and ‘actual access’ definitions of privacy, once revised in the face of counter-examples involving inferred information, converge. Chapter 3, which considers how AI impacts the normative aspect of privacy, particularly the value of privacy, argues that AI affects the social value of privacy, which depends on trust, as this dimension of privacy is constituted when AI models perform accurately. Chapter 4 examines how AI impacts the normative aspect of privacy, particularly the right to privacy, and it argues that, although accessing information uncovered by AI models raises concerns about the privacy of algorithmically designed groups, the right to privacy cannot be recognised for such groups. This is the disruptive feature of AI that has led to consideration of new approaches other than the traditional one, which involves recognising the right to privacy, to protect the privacy of these groups. Instead of recognising the right to privacy for algorithmically designed groups, this chapter suggests taking a moral principle for the moral obligation of protecting vulnerable groups within an ethics of vulnerability. -/- Part II concerns the second stage of the PIA and consists of one chapter that responds to RQ2. Chapter 5, in addition to evaluating whether AI that processes personal information and develops models complies with the GDPR, also assesses whether the GDPR adequately addresses the privacy issues raised by AI. It specifically focuses on group privacy and argues that GDPR has limitations in protecting the privacy of algorithmically designed groups and that the privacy of such vulnerable entities must be considered in the context of privacy and data protection. -/- Part III, which is related to the third stage of the PIA, also consists of one chapter that responds to RQ3. Chapter 6 proposes design requirements to protect privacy by integrating privacy into systems and argues that privacy is instrumentally valuable for the sake of autonomy. Accordingly, to embed the value of privacy into systems, design requirements are articulated through the translation of norms that promote and protect autonomy. (shrink)

The research methodology involves data preprocessing, feature engineering, model training, and performance evaluation. We employ optimization methods such as Genetic Algorithms and Grid Search to fine-tune model parameters, ensuring robust and generalizable models. The dataset used includes patient medical records, with features like age, blood pressure, cholesterol levels, and lifestyle habits serving as inputs for the ML models. Evaluation metrics, including accuracy, precision, recall, F1-score, and the area under the ROC curve (AUC-ROC), assess the model's predictive power.

To create fair and accountable AI and robotics, we need precise regulation and better methods to certify, explain, and audit inscrutable systems.

Abstract: Ensuring the proactive detection of transaction risks is paramount for financial institutions, particularly in the context of managing credit scores. In this study, we compare different machine learning algorithms to effectively and efficiently. The algorithms used in this study were: MLogisticRegressionCV, ExtraTreeClassifier,LGBMClassifier,AdaBoostClassifier, GradientBoostingClassifier,Perceptron,RandomForestClassifier,KNeighborsClassifier,BaggingClassifier, DecisionTreeClassifier, CalibratedClassifierCV, LabelPropagation, Deep Learning. The dataset was collected from Kaggle depository. It consists of 164 rows and 8 columns. The best classifier with unbalanced dataset was the LogisticRegressionCV. The Accuracy 100.0%, precession 100.0%,Recall100.0% (...) and the F1-score 100.0%. However, the best classifier with balanced dataset was the LogisticRegressionCV. The Accuracy 100.0%, precession 100.0%, Recall 100.0% and the F1-score 100.0%. (shrink)

Cloud computing has transformed data management and storage by providing unmatched scalability, flexibility, and cost-effectiveness. However, rising cloud storage use has raised data security and privacy issues. As sensitive data being outsourced to third-party cloud providers, security is crucial. Traditional encryption methods secure data but make data recovery difficult. Specifically, efficiently searching encrypted data without compromising security is difficult.

: Driver drowsiness is a significant factor contributing to road accidents, resulting in severe injuries and fatalities. This study presents an optimized approach for detecting driver drowsiness using machine learning techniques. The proposed system utilizes real-time data to analyze driver behavior and physiological signals to identify signs of fatigue. Various machine learning algorithms, including Support Vector Machines (SVM), Convolutional Neural Networks (CNN), and Random Forest, are explored for their efficacy in detecting drowsiness. The system incorporates an (...) optimization technique—such as Genetic Algorithms (GA) or Particle Swarm Optimization (PSO)—to enhance the accuracy and response time of the detection process. The integration of optimization methods ensures that the model adapts to various driving conditions and individual differences, providing a more reliable and robust detection mechanism. Data from multiple sources, including camera feeds and wearable sensors, are used to train and validate the models, ensuring a comprehensive understanding of drowsiness indicators. (shrink)