Membership Inference Attacks

Also known as MIA

Overview

Membership inference attacks ask whether a particular record, person, or dataset contributed to a model’s training, helping assess privacy risks. Black-box attacks use outputs such as loss, confidence, or generated text, while white-box methods analyze gradients and internal representations; LiRA and RMIA are prominent reference-model approaches. Researchers apply these methods to language, vision, generative, recommender, and federated models, and study defenses including differential privacy, regularization, and limits on exposed signals. A central challenge is that results can change sharply with attacker access, distribution shift, and false-positive rates, so reliable audits must distinguish practical privacy risks from apparent attack success under unrealistic assumptions.

Latest papers

CardsList

125 papers14 papers in the last four weeks, up 17% on the four weeks before. 0.1% of all new papers.

  1. Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning

    Jan 10, 2026Quan Minh Nguyen, Min-Seon Kim, Hoang M. Ngo +3Membership Inference AttacksFederated Fine-Tuning

  2. Estimating Model-Level Membership Inference Vulnerability Without Reference Models

    Oct 22, 2025Euodia Dodd, Nataša Krčo, Igor Shilov +2Membership Inference Attacks

  3. Auditing Information Disclosure During Large-Scale Gradient-Based Training via Gradient Uniqueness

    Oct 13, 2025Sleem Abdelghafar, Maryam Aliakbarpour, Christopher JermaineData LeakagePrivacy Auditing

  4. Membership Inference Attacks on Recommender System: A Survey

    Sep 14, 2025Jiajie He, Xintong Chen, Xinyang Fang +4Membership Inference AttacksPrivacy-Preserving ML

  5. The Sample Complexity of Membership Inference and Privacy Auditing

    Aug 26, 2025Mahdi Haghifam, Adam Smith, Jonathan UllmanMembership Inference AttacksSample Complexity