More than 1600 Google employees are demanding that the company stop selling technology to police departments. "We're disappointed to know that Google is still selling to police forces, and advertises its connection with police forces as somehow progressive, and seeks more expansive sales rather than severing ties with police and joining the millions who want to defang and defund these institutions," the letter reads, according to Techcrunch. "Why help the institutions responsible for the knee on George Floyd's neck to be more effective organizationally? Not only that, but the same Clarkstown police force being advertised by Google as a success story has been sued multiple times for illegal surveillance of Black Lives Matter organizers." The letter, signed by 1666 employees, was addressed to Alphabet CEO Sundar Pichai.

The news: An open letter from a growing coalition of AI researchers is calling out scientific publisher Springer Nature for a conference paper it reportedly planned to include in its forthcoming book Transactions on Computational Science & Computational Intelligence. The paper, titled "A Deep Neural Network Model to Predict Criminality Using Image Processing," presents a face recognition system purportedly capable of predicting whether someone is a criminal, according to the original press release. It was developed by researchers at Harrisburg University and was due to be presented at a forthcoming conference. The demands: Citing the work of leading Black AI scholars, the letter debunks the scientific basis of the paper and asserts that crime-prediction technologies are racist. It also lists three demands: 1) for Springer Nature to rescind its offer to publish the study; 2) for it to issue a statement condemning the use of statistical techniques such as machine learning to predict criminality and acknowledging its role in incentivizing such research; and 3) for all scientific publishers to commit to not publishing similar papers in the future.

Automated facial recognition technology that searches for people in public places breaches privacy rights and will "radically" alter the way Britain is policed, the court of appeal has been told. At the opening of a legal challenge against the use by South Wales police of the mass surveillance system, lawyers for the civil rights organisation Liberty argued that it is also racially discriminatory and contrary to data protection laws. In written submissions to the court, Dan Squires QC, who is acting for Liberty and Ed Bridges, a Cardiff resident, said that the South Wales force had already captured the biometrics of 500,000 faces, the overwhelming majority of whom are not suspected of any wrongdoing. Bridges, 37, whose face was scanned while he was Christmas shopping in Cardiff in 2017 and at a peaceful anti-arms protest outside the city's Motorpoint Arena in 2018, says the use of automatic facial recognition (AFR) by South Wales police caused him "distress". The case has been brought after South Wales police and the Home Office won a high court case last year that effectively gave the green light for national deployment of the technology.

Enabling machines to legal balancing is a non-trivial task challenged by a multitude of factors some of which are addressed and explored in this work. We propose a holistic approach to formal modeling at different abstraction layers supported by a pluralistic framework in which the encoding of an ethico-legal value and upper ontology is developed in combination with the exploration of a formalization logic, with legal domain knowledge and with exemplary use cases until a reflective equilibrium is reached. Our work is enabled by a meta-logical approach to universal logical reasoning and it applies the recently introduced \logikey\ methodology for designing normative theories for ethical and legal reasoning. The particular focus in this paper is on the formalization and encoding of a value ontology suitable e.g. for explaining and resolving legal conflicts in property law (wild animal cases).

Algorithmic bias is the systematic preferential or discriminatory treatment of a group of people by an artificial intelligence system. In this work we develop a random-effects based metric for the analysis of social bias in supervised machine learning prediction models where model outputs depend on U.S. locations. We define a methodology for using U.S. Census data to measure social bias on user attributes legally protected against discrimination, such as ethnicity, sex, and religion, also known as protected attributes. We evaluate our method on the Strategic Subject List (SSL) gun-violence prediction dataset, where we have access to both U.S. Census data as well as ground truth protected attributes for 224,235 individuals in Chicago being assessed for participation in future gun-violence incidents. Our results indicate that quantifying social bias using U.S. Census data provides a valid approach to auditing a supervised algorithmic decision-making system. Using our methodology, we then quantify the potential social biases of 100 million ridehailing samples in the city of Chicago. This work is the first large-scale fairness analysis of the dynamic pricing algorithms used by ridehailing applications. An analysis of Chicago ridehailing samples in conjunction with American Community Survey data indicates possible disparate impact due to social bias based on age, house pricing, education, and ethnicity in the dynamic fare pricing models used by ridehailing applications, with effect-sizes of 0.74, 0.70, 0.34, and -0.31 (using Cohen's d) for each demographic respectively. Further, our methodology provides a principled approach to quantifying algorithmic bias on datasets where protected attributes are unavailable, given that U.S. geolocations and algorithmic decisions are provided.

Machine learning becomes increasingly important to tune or even synthesize the behavior of safety-critical components in highly non-trivial environments, where the inability to understand learned components in general, and neural nets in particular, poses serious obstacles to their adoption. Explainability and interpretability methods for learned systems have gained considerable academic attention, but the focus of current approaches on only one aspect of explanation, at a fixed level of abstraction, and limited if any formal guarantees, prevents those explanations from being digestible by the relevant stakeholders (e.g., end users, certification authorities, engineers) with their diverse backgrounds and situation-specific needs. We introduce Fanoos, a flexible framework for combining formal verification techniques, heuristic search, and user interaction to explore explanations at the desired level of granularity and fidelity. We demonstrate the ability of Fanoos to produce and adjust the abstractness of explanations in response to user requests on a learned controller for an inverted double pendulum and on a learned CPU usage model.

Nowadays, deep neural networks are widely used in mission critical systems such as healthcare, self-driving vehicles, and military which have direct impact on human lives. However, the black-box nature of deep neural networks challenges its use in mission critical applications, raising ethical and judicial concerns inducing lack of trust. Explainable Artificial Intelligence (XAI) is a field of Artificial Intelligence (AI) that promotes a set of tools, techniques, and algorithms that can generate high-quality interpretable, intuitive, human-understandable explanations of AI decisions. In addition to providing a holistic view of the current XAI landscape in deep learning, this paper provides mathematical summaries of seminal work. We start by proposing a taxonomy and categorizing the XAI techniques based on their scope of explanations, methodology behind the algorithms, and explanation level or usage which helps build trustworthy, interpretable, and self-explanatory deep learning models. We then describe the main principles used in XAI research and present the historical timeline for landmark studies in XAI from 2007 to 2020. After explaining each category of algorithms and approaches in detail, we then evaluate the explanation maps generated by eight XAI algorithms on image data, discuss the limitations of this approach, and provide potential future directions to improve XAI evaluation.

In the next coming years, space activities are expected to undergo a radical transformation with the emergence of new satellite systems or new services which will incorporate the contributions of artificial intelligence and machine learning defined as covering a wide range of innovations from autonomous objects with their own decision-making power to increasingly sophisticated services exploiting very large volumes of information from space. This chapter identifies some of the legal and ethical challenges linked to its use. These legal and ethical challenges call for solutions which the international treaties in force are not sufficient to determine and implement. For this reason, a legal methodology must be developed that makes it possible to link intelligent systems and services to a system of rules applicable thereto. It discusses existing legal AI-based tools amenable for making space law actionable, interoperable and machine readable for future compliance tools.

In this paper, we initiate the study of fair clustering that ensures distributional similarity among similar individuals. In response to improving fairness in machine learning, recent papers have investigated fairness in clustering algorithms and have focused on the paradigm of statistical parity/group fairness. These efforts attempt to minimize bias against some protected groups in the population. However, to the best of our knowledge, the alternative viewpoint of individual fairness, introduced by Dwork et al. (ITCS 2012) in the context of classification, has not been considered for clustering so far. Similar to Dwork et al., we adopt the individual fairness notion which mandates that similar individuals should be treated similarly for clustering problems. We use the notion of $f$-divergence as a measure of statistical similarity that significantly generalizes the ones used by Dwork et al. We introduce a framework for assigning individuals, embedded in a metric space, to probability distributions over a bounded number of cluster centers. The objective is to ensure (a) low cost of clustering in expectation and (b) individuals that are close to each other in a given fairness space are mapped to statistically similar distributions. We provide an algorithm for clustering with $p$-norm objective ($k$-center, $k$-means are special cases) and individual fairness constraints with provable approximation guarantee. We extend this framework to include both group fairness and individual fairness inside the protected groups. Finally, we observe conditions under which individual fairness implies group fairness. We present extensive experimental evidence that justifies the effectiveness of our approach.

Beyond the possible misuses of technology, there is an increased awareness that these processes are not neutral and can reproduce and amplify past and current structural inequalities [1, 2]. Within this context, particular interest is paid to the role of machine learning (ML) with well known examples of models biased against historically discriminated groups [3, 4, 5] or the intersection of these groups [6, 7]. Fairness in ML has emerged as a community initially motivated to develop technological solutions to the disparate impact and treatment by biased algorithms [8, 9, 10, 11, 5] that also moves to a broader and multi-disciplinary understanding of the issues of socio-technological interventions [12, 13, 14, 15]. This work contribute to this field by studying how far bias mitigation can go whilst satisfying the accuracy and transparency of the models, thus providing a tool for a wider understanding of the technological boundaries of socio-technical proposals. Bias mitigation techniques can broadly be divided into three non-exclusive categories [16]: (1) preprocessing, (2) inprocessing, and (3) postprocessing. The preprocessing techniques attempt to learn new representations of data to satisfy fairness definitions. The inprocessing methods involve modifying the classifier algorithm by adding a fairness constraint to the optimization problem. The postprocessing methods aim at removing discriminatory decisions after the model is trained. Normally, in inprocessing approaches the fairness criteria are used as an optimization constraint rather than as a guide to build a more equitable prediction model.