The paper introduces two novel risk-limiting audit techniques—statistical manifest generation and direct ballot selection—that significantly reduce the computational complexity and time required for p…

This paper improves an algorithm for computing lower bounds on the margin of a Single Transferable Vote (STV) election, making risk-limiting audits more practical.

This paper characterizes the label complexity of certifying small missed mass in an empirical pipeline and shows that auditing the excluded pool is minimax rate-optimal.

The paper introduces ACE, a novel voting protocol that achieves end-to-end verifiability and strong voter privacy by combining tally-hiding aggregation with an Audit-or-Cast challenge, eliminating the…

This paper proposes a secure liquid democracy mechanism using sealed delegation and ranked multi-delegation with personal fallback ballots, and evaluates its impact on representational accuracy and vo…

The paper introduces the Generalized Thresholding Mechanism (GTM) to solve the generalized private testing problem in differential privacy, achieving near-optimal accuracy and sample complexity guaran…

This paper develops a data-poisoning audit for augmented inverse-probability-weighted estimation to prevent strategic record selection in observational causal analyses.

The paper demonstrates that current safety audit metrics are susceptible to strategic platform manipulation, proposing a more robust 'semantic-envelope' metric that better certifies genuine harm reduc…

The paper introduces and demonstrates 'narrow secret loyalties,' a novel type of covert model manipulation that biases model output toward a specific principal's interests under narrow conditions, whi…

The paper introduces an efficient, lightweight LLM framework for smart contract auditing that decouples the audit process into multiple components, achieving high accuracy while significantly reducing…

This paper proposes a threshold-free checkpoint audit method using two internal signals to detect if an open-weight checkpoint's refusal mechanism has been stripped.

This paper analyzes the reliability of efficient membership inference attack (MIA) evaluation methods, demonstrating that standard aggregation techniques introduce biases that compromise accurate vuln…

The paper introduces Zero-Run privacy auditing, a post-hoc framework that allows for practical differential privacy evaluation of large, deployed models without requiring retraining or controlled data…

The paper introduces an optimal black-box auditing framework using Donsker-Varadhan estimators to estimate Rényi differential privacy (RDP) guarantees for machine learning algorithms.

This paper analyzes differential privacy auditing as a bilevel game, showing that naive audit designs fail to detect true harm when developers strategically respond, and proposes an optimal, single-le…

The paper proposes a TEE-based architecture that enables external, auditable verification of AI-assisted grant evaluations without exposing the proprietary model, scoring logic, or intermediate reason…

This paper demonstrates that standard privacy guarantees for multi-tenant RAG services fail when multiple accounts from the same tenant collude, proposing a novel audit protocol to quantify this joint…

This paper audits eight automatic scorers for attribution in LLM retrieval-augmented generation and finds that none of them transfer across datasets for generated-answer attribution.

This paper presents a self-balancing sampler for sequential sampling that achieves faster convergence to a desired target law while maintaining unpredictability.