Related papers: A Game-Theoretic Analysis of Auditing Differential…
Companies report on their financial performance for decades. More recently they have also started to report on their environmental impact and their social responsibility. The latest trend is now to deliver one single integrated report where…
A surge in data-driven applications enhances everyday life but also raises serious concerns about private information leakage. Hence many privacy auditing tools are emerging for checking if the data sanitization performed meets the privacy…
Artificial Intelligence (AI) is increasingly used to make important decisions about people. While issues of AI bias and proxy discrimination are well explored, less focus has been paid to the harms created by profiling based on groups that…
The rapid deployment of AI systems in high-stakes domains, including those classified as high-risk under the The EU AI Act (Regulation (EU) 2024/1689), has intensified the need for reliable compliance auditing. For binary classifiers,…
Privacy auditing aims to empirically assess privacy leakage in machine learning models using membership inference attacks (MIAs), and to derive lower bounds on differential privacy (DP) parameters. Recent one-run auditing methods address…
Many organizations use algorithms that have a disparate impact, i.e., the benefits or harms of the algorithm fall disproportionately on certain social groups. Addressing an algorithm's disparate impact can be challenging, however, because…
Certainty around the regulatory environment is crucial to enable responsible AI innovation and foster the social acceptance of these powerful new technologies. One notable source of uncertainty is, however, that the existing legal liability…
As AI systems evolve from isolated predictors into complex, heterogeneous ecosystems of foundation models and specialized adapters, distinguishing genuine behavioral novelty from functional redundancy becomes a critical governance…
Benchmarks are important measures to evaluate safety and compliance of AI models at scale. However, they typically do not offer verifiable results and lack confidentiality for model IP and benchmark datasets. We propose Attestable Audits,…
As the rapid proliferation of AI systems and harms spurs efforts in AI governance around the world, prioritizing among competing policy options has become increasingly challenging for policymakers and researchers. We introduce a methodology…
The EU Artificial Intelligence (AI) Act directs businesses to assess their AI systems to ensure they are developed in a way that is human-centered and trustworthy. The rapid adoption of AI in the industry has outpaced ethical evaluation…
As the possibilities for Artificial Intelligence (AI) have grown, so have concerns regarding its impacts on society and the environment. However, these issues are often raised separately; i.e. carbon footprint analyses of AI models…
Predictive algorithms are now used to help distribute a large share of our society's resources and sanctions, such as healthcare, loans, criminal detentions, and tax audits. Under the right circumstances, these algorithms can improve the…
While a substantial amount of work has recently been devoted to enhance the performance of computational Authorship Identification (AId) systems, little to no attention has been paid to endowing AId systems with the ability to explain the…
While significant progress has been made in conventional fairness-aware machine learning (ML) and differentially private ML (DPML), the fairness of privacy protection across groups remains underexplored. Existing studies have proposed…
Harm reporting in Artificial Intelligence (AI) currently lacks a structured process for disclosing and addressing algorithmic flaws, relying largely on an ad-hoc approach. This contrasts sharply with the well-established Coordinated…
AI systems are becoming increasingly complex, ubiquitous and autonomous, leading to increasing concerns about their impacts on individuals and society. In response, researchers have begun investigating how to ensure that the methods…
AI systems are being deployed to support human decision making in high-stakes domains. In many cases, the human and AI form a team, in which the human makes decisions after reviewing the AI's inferences. A successful partnership requires…
The integration of Artificial Intelligence (AI) systems into technologies used by young digital citizens raises significant privacy concerns. This study investigates these concerns through a comparative analysis of stakeholder perspectives.…
Employers are adopting algorithmic hiring technology throughout the recruitment pipeline. Algorithmic fairness is especially applicable in this domain due to its high stakes and structural inequalities. Unfortunately, most work in this…