Abstract A membership inference attack (MIA) against a machine-learning model enables an attacker to determine whether a given data record was part of the model’s training data or not. In this paper, we provide an in-depth study of the phenomenon of disparate vulnerability against MIAs: unequal success rate of MIAs against different population subgroups. We first establish necessary and sufficient conditions for MIAs to be prevented, both on average and for population subgroups, using a notion of distributional generalization. Second, we derive connections of disparate vulnerability to algorithmic fairness and to differential privacy. We show that fairness can only prevent disparate vulnerability against limited classes of adversaries. Differential privacy bounds disparate vulnerability but can significantly reduce the accuracy of the model. We show that estimating disparate vulnerability by naïvely applying existing attacks can lead to overestimation. We then establish which attacks are suitable for estimating disparate vulnerability, and provide a statistical framework for doing so reliably. We conduct experiments on synthetic and real-world data finding significant evidence of disparate vulnerability in realistic settings.

Abstract There is growing evidence that SARS-CoV-2 can be transmitted beyond close proximity contacts, in particular in closed and crowded environments with insufficient ventilation. To help mitigation efforts, contact tracers need a way to notify those who were present in such environments at the same time as infected individuals. Neither traditional human-based contact tracing powered by handwritten or electronic lists, nor Bluetooth-enabled proximity tracing can handle this problem efficiently. In this paper, we propose CrowdNotifier, a protocol that can complement manual contact tracing by efficiently notifying visitors of venues and events with SARS-CoV-2-positive attendees. We prove that CrowdNotifier provides strong privacy and abuse-resistance, and show that it can scale to handle notification at a national scale.

New consent management platforms (CMPs) have been introduced to the web to conform with the EU's General Data Protection Regulation, particularly its requirements for consent when companies collect and process users' personal data. This work analyses how the most prevalent CMP designs affect people's consent choices. We scraped the designs of the five most popular CMPs on the top 10,000 websites in the UK (n=680). We found that dark patterns and implied consent are ubiquitous; only 11.8% meet our minimal requirements based on European law. Second, we conducted a field experiment with 40 participants to investigate how the eight most common designs affect consent choices. We found that notification style (banner or barrier) has no effect; removing the opt-out button from the first page increases consent by 22-23 percentage points; and providing more granular controls on the first page decreases consent by 8-20 percentage points. This study provides an empirical basis for the necessary regulatory action to enforce the GDPR, in particular the possibility of focusing on the centralised, third-party CMP services as an effective way to increase compliance.

Data-driven decision-making consequential to individuals raises important questions of accountability and justice. Indeed, European law provides individuals limited rights to 'meaningful information about the logic' behind significant, autonomous decisions such as loan approvals, insurance quotes, and CV filtering. We undertake three experimental studies examining people's perceptions of justice in algorithmic decision-making under different scenarios and explanation styles. Dimensions of justice previously observed in response to human decision-making appear similarly engaged in response to algorithmic decisions. Qualitative analysis identified several concerns and heuristics involved in justice perceptions including arbitrariness, generalisation, and (in)dignity. Quantitative analysis indicates that explanation styles primarily matter to justice perceptions only when subjects are exposed to multiple different styles---under repeated exposure of one style, scenario effects obscure any explanation effects. Our results suggests there may be no 'best' approach to explaining algorithmic decisions, and that reflection on their automated nature both implicates and mitigates justice dimensions.

Calls for heightened consideration of fairness and accountability in algorithmically-informed public decisions-like taxation, justice, and child protection-are now commonplace. How might designers support such human values? We interviewed 27 public sector machine learning practitioners across 5 OECD countries regarding challenges understanding and imbuing public values into their work. The results suggest a disconnect between organisational and institutional realities, constraints and needs, and those addressed by current research into usable, transparent and 'discrimination-aware' machine learning-absences likely to undermine practical initiatives unless addressed. We see design opportunities in this disconnect, such as in supporting the tracking of concept drift in secondary data sources, and in building usable transparency tools to identify risks and incorporate domain knowledge, aimed both at managers and at the 'street-level bureaucrats' on the frontlines of public service. We conclude by outlining ethical challenges and future directions for collaboration in these high-stakes applications.

Recent work has explored how to train machine learning models which do not discriminate against any subgroup of the population as determined by sensitive attributes such as gender or race. To avoid disparate treatment, sensitive attributes should not be considered. On the other hand, in order to avoid disparate impact, sensitive attributes must be examined, e.g., in order to learn a fair model, or to check if a given model is fair. We introduce methods from secure multi-party computation which allow us to avoid both. By encrypting sensitive attributes, we show how an outcome-based fair model may be learned, checked, or have its outputs verified and held to account, without users revealing their sensitive attributes.

Cite as: Michael Veale and Lilian Edwards, 'Clarity, Surprises, and Further Questions in the Article 29 Working Party Draft Guidance on Automated Decision-Making and Profiling' (forthcoming) Computer Law and Security ReviewThe new Article 29 Data Protection Working Party’s draft guidance on automated decision-making and profiling seeks to clarify the European data protection (DP) law’s little-used right to prevent automated decision-making, as well as the provisions around profiling more broadly, in the run-up to the General Data Protection Regulation. In this paper, we analyse these new guidelines in the context of recent scholarly debates and technological concerns. They foray into the less-trodden areas of bias and non-discrimination, the significance of advertising, the nature of “solely” automated decisions, impacts upon groups and the inference of special categories of data — at times, appearing more to be making or extending rules than to be interpreting them. At the same time, they provide only partial clarity — and perhaps even some extra confusion — around both the much discussed “right to an explanation” and the apparent prohibition on significant automated decisions concerning children. The Working Party appear to feel less mandated to adjudicate in these conflicts between the recitals and the enacting articles than to explore altogether new avenues. Nevertheless, the directions they choose to explore are particularly important ones for the future governance of machine learning and artificial intelligence in Europe and beyond.