arXiv:2605. 19847v2 Announce Type: replace-cross Abstract: Multi-tenant RAG services often treat the account as the privacy boundary: each account receives an $(\varepsilon_{\text{acc}},\delta_{\text{acc}})$-DP retrieval guarantee against the tenant index.
arXiv:2606. 14518v1 Announce Type: new Abstract: The removal of learned data from Machine Learning models through Machine Unlearning (MU) has been widely studied; however, there has yet to be an agreed-upon scheme for auditing MU.
arXiv:2606. 00414v1 Announce Type: new Abstract: When many reinforcement-learning policies achieve near-optimal return, a post-hoc auditor may have to distinguish among many behaviorally distinct but return-equivalent policies.
arXiv:2605. 27292v2 Announce Type: replace Abstract: 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.
arXiv:2607. 12188v1 Announce Type: new Abstract: Enterprise Retrieval-Augmented Generation (RAG) deployments face a critical governance gap: while LLM generation cost is metered per token, the retrieval layer - vector memory, similarity compute, and embedding API calls - remains an unattributed shared cost, enabling invisible cross-subsidization among tenants.
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.
arXiv:2606. 02563v1 Announce Type: new Abstract: Heterogeneous Differential Privacy (HDP) in Federated Learning (FL) allows clients to select individual privacy budgets ($\varepsilon_i$) according to institutional policies and data sensitivity.
arXiv:2607. 26385v1 Announce Type: cross Abstract: Empirical work on algorithmic collusion asks one question of the data: are prices supracompetitive?
arXiv:2607. 16620v1 Announce Type: cross Abstract: Differential privacy (DP) is increasingly deployed to limit membership inference risk in machine-learning systems.
arXiv:2602. 11510v3 Announce Type: replace Abstract: Multi-agent Large Language Model (LLM) systems create privacy risks that current output-only benchmarks cannot measure.
arXiv:2606. 00152v1 Announce Type: cross Abstract: LLM-based agents are rapidly advancing, autonomously invoking external tools to complete multi-step tasks for users.
arXiv:2607. 13928v1 Announce Type: cross Abstract: Whistleblowers are a key safeguard against organizational wrongdoing, but the threat of retaliation deters reporting.
Empirical work on algorithmic collusion asks one question of the data: are prices supracompetitive? We show this can be answered "no" by a conspiracy that is nonetheless profitable.