Audit finds DP violations in 5 of 9 mechanisms in Apple's framework due to insecure floating-point samplers and disabled local DP in secure aggregation, impacting 87% of macOS Sonoma and 68% of Sequoia data collection.
Auditingf-differential privacy in one run
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
Zero-Run auditing supplies valid lower bounds on differential privacy parameters from fixed member and non-member datasets by modeling and correcting distribution-shift confounding via causal-inference techniques.
A hypothesis-testing framework with class-restricted Donsker-Varadhan estimators provides optimal non-asymptotic confidence intervals and minimax lower bounds for black-box auditing of Rényi DP guarantees.
Indistinguishability-based privacy is incomparable to extractability in LLMs, and a new (l, b)-inextractability definition with rank-based bounds provides a tighter measure of extraction risk than prior proxies.
DPrivBench is a new benchmark for evaluating LLMs on differential privacy reasoning, with results showing good performance on textbook mechanisms but substantial failures on advanced algorithms.
citing papers explorer
-
Auditing Apple's DifferentialPrivacy.framework: Implementation Bugs, Misconfigurations, and Practical Risks
Audit finds DP violations in 5 of 9 mechanisms in Apple's framework due to insecure floating-point samplers and disabled local DP in secure aggregation, impacting 87% of macOS Sonoma and 68% of Sequoia data collection.
-
Privacy Auditing with Zero (0) Training Run
Zero-Run auditing supplies valid lower bounds on differential privacy parameters from fixed member and non-member datasets by modeling and correcting distribution-shift confounding via causal-inference techniques.
-
Optimal Guarantees for Auditing R\'enyi Differentially Private Machine Learning
A hypothesis-testing framework with class-restricted Donsker-Varadhan estimators provides optimal non-asymptotic confidence intervals and minimax lower bounds for black-box auditing of Rényi DP guarantees.
-
Beyond Indistinguishability: Measuring Extraction Risk in LLM APIs
Indistinguishability-based privacy is incomparable to extractability in LLMs, and a new (l, b)-inextractability definition with rank-based bounds provides a tighter measure of extraction risk than prior proxies.
-
DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
DPrivBench is a new benchmark for evaluating LLMs on differential privacy reasoning, with results showing good performance on textbook mechanisms but substantial failures on advanced algorithms.