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

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 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 a Gaussian Differential Privacy (GDP)-based auditing framework to provide the first tight audits of privacy guarantees for state-of-the-art synthetic data generators like MST and…

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 a novel realization-level privacy filtering approach that improves utility in differentially private data release by accounting for actual leakage rather than worst-case per-round…

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…

The paper demonstrates that the current per-token billing model for LLMs is susceptible to systematic overcharging because auditing frameworks must rely on evidence provided by the very companies that…

The paper demonstrates that the current per-token billing model for LLMs is susceptible to systematic inflation because auditing frameworks must rely on evidence provided by the service provider, crea…

The paper introduces BadSkill, a novel backdoor attack formulation that targets third-party agent skills by poisoning the embedded model artifacts, achieving high attack success rates across various m…

The paper models healthcare mechanism design as program synthesis, demonstrating that an optimized, mixed-objective program can eliminate up-coding and reduce patient rejection while maintaining finan…

This paper corrects the theoretical analysis of DP-SGD by identifying that common implementations, which use batch averaging, result in weaker privacy guarantees than previously reported.

The paper develops a unified theoretical framework to systematically characterize the optimal privacy-utility trade-off (PUT) and optimal Local Differential Privacy (LDP) channels for general statisti…

The paper demonstrates that by introducing carefully designed correlations among locally added noise variables, local differential privacy mechanisms can achieve an estimation cost matching the optima…

This paper develops a differential privacy framework to analyze and optimize privacy leakage from AI agent responses that utilize sensitive enterprise data, focusing on deriving optimal generation par…

The paper introduces DPrivBench, a new benchmark to test whether large language models (LLMs) can automate the complex reasoning required to verify differential privacy guarantees for algorithms.

The paper proposes a robust causal decision framework to measure advertising incrementality despite multiple sources of privacy-induced signal degradation, providing certified decisions on the strengt…

The paper proposes a mutagenic incentive intervention approach that mitigates collusion in embodied multi-agent systems by reshaping agents' payoff structures, effectively inducing defection and maint…

The paper introduces PrivacyPeek, a new benchmark that audits the acquisition stage of LLM-based agents to demonstrate that unnecessary acquisition of sensitive data is a widespread and critical priva…

The paper introduces PrivacyPeek, a new benchmark that audits the acquisition stage of LLM-based agents to show that unnecessary and sensitive data acquisition is a widespread and critical privacy vul…