arXiv:2610.10199v1 Announce Type: new Abstract: Emerging legislation requires large language models (LLMs) to be audited for compliance with regulatory standards, particularly fairness. Such black-bo...
arXiv:2608. 04365v1 Announce Type: new Abstract: Audits have emerged as a critical instrument for algorithmic governance, providing a mechanism for external scrutiny and governance of machine learning models.
arXiv:2606. 30338v1 Announce Type: new Abstract: External evaluations are becoming increasingly central to the governance of AI systems.
arXiv:2608. 00568v1 Announce Type: new Abstract: Fairness audits are increasingly mandated in high-stakes applications such as hiring, lending, and automated decision-making.
arXiv:2608. 06469v1 Announce Type: cross Abstract: Collaborative machine learning among financial institutions must be both group-fair and robust against deliberate adversarial manipulation.
arXiv:2609.40034v1 Announce Type: cross Abstract: Over the past decade, Machine Learning (ML) has been trained under dual objectives: minimizing prediction error via Empirical Risk Minimization (ERM)...
arXiv:2507. 20708v3 Announce Type: replace Abstract: 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.
arXiv:2601.03087v2 Announce Type: replace Abstract: Large Language Models (LLMs) exhibit systematic biases across demographic groups. Auditing is proposed as an accountability tool for black-box LLM...
Giskard is a scalable protocol for private and Byzantine‑robust decentralized aggregation in large‑scale learning. It organizes participants into a tree of committees of size O(log n) and computes a differentially private coordinate‑wise approximate median using secure multi‑party computation within each committee. Experiments with up to one million participants show that Giskard reduces per‑party communication by nearly three orders of magnitude compared to its closest competitors while maintaining robustness against up to n/4 Byzantine parties.
arXiv:2608.24818v1 Announce Type: new Abstract: Neighborhood-based fairness audits evaluate individual fairness by comparing predictions among similar individuals in feature space. Despite their wide...
The paper introduces DISCERN, a two-tier protocol for certifying that updates to production models do not increase risk. It first uses unlabeled data to detect benign updates based on disagreement rates, then selectively labels only disagreements through an anytime-valid confidence sequence. The method achieves finite-sample validity with label-complexity bounds of order ρ²/ε², demonstrating significant label savings and strong empirical performance across 14,000+ audit streams.
arXiv:2605. 07674v2 Announce Type: replace-cross Abstract: Regulatory audits of AI systems increasingly rely on differential privacy (DP) to protect training data and model internals.