相关论文: Transparency, Compliance, And Contestability When …

Interpretability research aims to bridge the gap between empirical success and our scientific understanding of the inner workings of large language models (LLMs). However, most existing research focuses on analyzing a single mechanism, such…

Explainable systems expose information about why certain observed effects are happening to the agents interacting with them. We argue that this constitutes a positive flow of information that needs to be specified, verified, and balanced…

Critical examinations of AI systems often apply principles such as fairness, justice, accountability, and safety, which is reflected in AI regulations such as the EU AI Act. Are such principles sufficient to promote the design of systems…

We propose a type system for a calculus of contracting processes. Processes can establish sessions by stipulating contracts, and then can interact either by keeping the promises made, or not. Type safety guarantees that a typeable process…

In this paper we examine algorithmic fairness from the perspective of law aiming to identify best practices and strategies for the specification and adoption of fairness definitions and algorithms in real-world systems and use cases. We…

The steady flow of social-media cases toward the Supreme Court shows a nation reworking its fundamental relationship with technology. The cases raise a host of questions ranging from difficult to impossible: how to nurture a vibrant public…

Adversarial training has been shown to be reliable in improving robustness against adversarial samples. However, the problem of adversarial training in terms of fairness has not yet been properly studied, and the relationship between…

AI has become pervasive in recent years, but state-of-the-art approaches predominantly neglect the need for AI systems to be contestable. Instead, contestability is advocated by AI guidelines (e.g. by the OECD) and regulation of automated…

This paper is preoccupied with the following question: given a (possibly opaque) learning system, how can we understand whether its behaviour adheres to governance constraints? The answer can be quite simple: we just need to "ask" the…

Regulating artificial intelligence (AI) has become necessary in light of its deployment in high-risk scenarios. This paper explores the proposal to extend legal personhood to AI and robots, which had not yet been examined through the lens…

The ethical imperative for technology should be first, do no harm. But digital innovations like AI and social media increasingly enable societal harms, from bias to misinformation. As these technologies grow ubiquitous, we need solutions to…

Policy enforcers are sophisticated runtime components that can prevent failures by enforcing the correct behavior of the software. While a single enforcer can be easily designed focusing only on the behavior of the application that must be…

Everyone wants clean air, peace and other public goods but is tempted to freeride on others' efforts. The usual way out of this dilemma is to impose norms, maintain reputations and incentivize individuals to contribute. In situations of…

Clearly, socio-economic freedom requires some extent of transparency regarding the implications of choices. In this paper, we review some established mechanisms for achieving such transparency, without any claim to completeness, and briefly…

What does it mean to claim that a physical or natural system computes? One answer, endorsed here, is that computing is about programming a system to behave in different ways. This paper offers an account of what it means for a physical…

Using dedicated software to represent or enact legislation or regulation has the advantage of solving the inherent ambiguity of legal texts and enabling the automation of compliance with legal norms. On the other hand, the so-called…

This paper introduces a scalable and secure contract-enforcement mechanism, called Cop, which can be applied to a broad range of multi-agent systems including small and large systems, time-critical systems, and systems-of-systems. Cop…

Building on the computer science concept of code smells, we initiate the study of law smells, i.e., patterns in legal texts that pose threats to the comprehensibility and maintainability of the law. With five intuitive law smells as running…

Computers are increasingly used to make decisions that have significant impact in people's lives. Often, these predictions can affect different population subgroups disproportionately. As a result, the issue of fairness has received much…

As AI becomes increasingly embedded in daily life, it has been shown to fail critically, cause harm, and spark public controversy, prompting affected communities, workers, and public-interest groups to contest it. Yet how these…