Overview

Privacy auditing studies how to measure what an adversary can learn about people from training data, released models, synthetic data, and AI system interactions. Common approaches include membership-inference and reconstruction attacks, optimized canaries, re-identification tests, and statistical tests that estimate privacy loss or certify risk; differential privacy provides a formal reference point. Audits increasingly examine realistic threat models, vulnerable subgroups, and information flows across tools and system components, while balancing privacy findings against utility. A central challenge is that attack results depend on assumptions, data, and evaluation choices, so a failed attack rarely proves that information cannot leak.

Latest papers

CardsList

85 papers7 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

  1. Quantifying Membership Inference Risks in Genomic Data Sharing: The Role of Attacker's Auxiliary Information

    Nov 13, 2026Maryam Ghasemian, Lynette Hammond Gerido, Erman AydayMembership Inference AttacksPrivacy Auditing

  2. PrivacyPR: A Dataset of Real-World Privacy Fixes for Benchmarking Privacy-Aware Code Review

    Nov 13, 2026Hua Yang, Aditya Bhardwaj, Shidong Pan +1Automated Code ReviewPrivacy Auditing

  3. Residual Attribute Leakage Is an Interface: Auditing Privacy Evaluation After Text De-identification

    Nov 3, 2026Tuan Thanh Duong, Joongmin Shin, Jeongho Yoon +2Privacy AuditingPrivacy Leakage in Language Models

  4. Accessed, never disclosed: Silent access to protected health information by medical artificial intelligence agents

    Nov 2, 2026Jae Wang Lee, Abhirup Banerjee, Yeong Chan LeeMedical AI AgentsPrivacy Protection for LLM Agents

  5. Shift-aware score transport for privacy auditing without retraining

    Oct 22, 2026Yaohong Yang, Gauri Pradhan, Qi Chen +2Privacy AuditingCovariate Shift

  6. Automated screening of privacy risks in medical AI

    Oct 21, 2026Konstantinos Vrettos, Eleftherios Tzanis, Haridimos Kondylakis +3Membership Inference AttacksPrivacy-Preserving ML

  7. Reliable Estimation of Differential Privacy under Selection Bias

    Oct 19, 2026Valentin Dorseuil, Meenatchi Sundaram Muthu Selva Annamalai, Jamal Atif +2Privacy AuditingDifferential Privacy

  8. QuasiLeak-Bench: Evaluating LLM-Based Privacy Detectors on Policy-Conditioned Quasi-Evidence Group Recovery

    Oct 15, 2026Yufan Zhu, Yangfan Jiang, Yang Fei +3Privacy Leakage in Language ModelsPrivacy Auditing

  9. Privacy in Personalized AI Is a System Property, Not Just a Model Property

    Sep 29, 2026Guillaume Salha-Galvan, Jiaying XuPrivacy Auditing

  10. The Text Beside the Image: Detection, Utility and Leakage for Trustworthy Multimodal Medical Data and Beyond

    Sep 27, 2026Andreas Maier, Monica Hinrichs-Mayer, Franziska Weber +4Privacy AuditingPII Detection

  11. Checking Leakage Witnesses versus Certifying Bounded Non-Leakage

    Sep 26, 2026Chao Feng, Burkhard StillerLanguage Model AuditingPrivacy Leakage in Language Models

  12. A Data-Interventional Framework for Auditing Privacy and Fairness in Generative Medical Imaging

    Sep 22, 2026Mischa Dombrowski, Bernhard KainzPrivacy AuditingDiffusion Models

  13. Empirical Auditing of Edge-Private Graph Generators

    Sep 21, 2026Anum Fatima, Stratis Limnios, James Adams +4Privacy AuditingEdge Inference

  14. Conformal Privacy Auditing: Calibrated Re-identification Attacks with Statistical Guarantees

    Sep 18, 2026Shuo Huang, Gholamreza Haffari, Xingliang Yuan +2Privacy AuditingPrivacy Leakage in Language Models

  15. Beyond Private Training: The New Landscape of AI Privacy

    Sep 16, 2026Sean Culatana, Kang LiPrivacy AuditingGraph-Based Retrieval

  16. ASLEval: Measuring Privacy Exposure Displacement in LLM Agent Sessions

    Sep 16, 2026Guosen Wu, Huizhen Huang, Guoxiong Long +2Privacy AuditingLLM Agent Evaluation

  17. Beyond EER: Multi-Dimensional Evaluation of Information Leakage in Speaker De-Identification

    Sep 16, 2026Seungmin Seo, Oleg Aulov, P. Jonathon Phillips +2Privacy AuditingBiometric Identification

  18. Canaries in the Bank: Auditing User-Level Privacy in Private Evolution

    Sep 11, 2026Sai Aparna Aketi, Enayat Ullah, Shripad GadePrivacy AuditingDifferentially Private Federated Learning

  19. GraphProfiler: Source-Linked Sensitive Attribute Inference via Personal Knowledge Graphs

    Sep 11, 2026Ahmed Sohair Khan, Estrid He, Chenglong Ma +2Privacy AuditingPrivacy Leakage in Language Models

  20. Predicting Privacy Leakage from Weight Spectral Density

    Sep 10, 2026Richard J. Preen, Jim SmithPrivacy AuditingMembership Inference Attacks

  21. Subgroup Membership Inference Audits of Differentially Private Synthetic Text

    Sep 9, 2026Yidan Sun, Viktor Schlegel, Srinivasan Nandakumar +2Privacy AuditingMembership Inference Attacks

  22. Auditing Patient Privacy in Medical Generative Models: Scalable Memorization Detection with DeepSSIM++

    Sep 3, 2026Antonio Scardace, Francesco Guarnera, Sebastiano Battiato +1Privacy AuditingMemorization in Generative Models

  23. Privacy Washing: Detecting Internal Contradictions in Privacy Policies

    Sep 2, 2026Thomas BrackinPrivacy Auditing

  24. Position: Privacy Is a Claim, Not a Property of Synthetic Data

    Sep 1, 2026Jiachen Zhao, Antonia Januszewicz, Taeho JungPrivacy AuditingPrivacy-Preserving ML

  25. MultiGait: A Multi-Sensor Multi-Perspective Multi-Session Biometric Inference Benchmark and its Dataset

    Sep 1, 2026Julian Todt, Felix Morsbach, Philip Dissert +1Privacy AuditingBiometric Identification

  26. Lensless Gaze Is Not Private by Default: Auditing Identity Leakage Across Disclosure Surfaces

    Aug 31, 2026Rahul Vimalkanth, Kaushik MitraPrivacy AuditingGaze Estimation

  27. Revisiting the Provable-Auditable Privacy Gap of DP-SGD

    Aug 28, 2026Saloni Modi, Srivi Balaji, Yusong Zhu +2Differential PrivacyDifferentially Private Stochastic Gradient Descent

  28. Picture the Epsilon: Pursuing Identity-Level Privacy Guarantees for Images

    Aug 17, 2026Arman Zareian Jahromi, Vishnu Bondalakunta, Mohammad Akbar Bin Shah +3Privacy AuditingDifferential Privacy

  29. A Human-LLM Teaming Framework for Privacy Risk Analysis: An Illustration with CBDC-Based Welfare Schemes

    Aug 17, 2026Sourya Joyee De, Abdessamad IminePrivacy Auditing