Tight Privacy Audit in One Run

arXiv:2509.08704 · cs.CR · Submitted 2025-09-10 · Read on arXiv

cs.CR

Submitted: 2025-09-10

Updated: 2026-09-18

Code: https://github.com/zihangxiang/tight-privacy-audit-in-one-run

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Differential Privacy — 23× in this paper · explained in 4 episodes
• Differentially Private — 14× in this paper · explained in 3 episodes
• Accuracy — 13× in this paper · explained in 1 episode
• Ablation — 3× in this paper · explained in 1 episode
• Privacy Loss Distribution — 3× in this paper
• Adam — 2× in this paper · explained in 2 episodes
• Differential Privacy (DP) — 2× in this paper · explained in 7 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Federated Learning — 1× in this paper · explained in 15 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning
• Auditing $f$-Differential Privacy in One Run
• Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
• On the Privacy Properties of Variants on the Sparse Vector Technique
• R'enyi Differential Privacy of the Sampled Gaussian Mechanism
• Debugging Differential Privacy: A Case Study for Privacy Auditing
• Privacy Audit as Bits Transmission: (Im)possibilities for Audit by One Run

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs