mlsanityData to 7 Oct 2026

Membership inference attacks

526 papers2 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: membership, inference, membership inference, privacy, attacks

Key facts. Membership inference attacks: 526 papers on arXiv since 2021 (data through 7 Oct 2026). 264 of its 526 mapped papers (50%) cite “Membership Inference Attacks From First Principles” (2021, arXiv 2112.03570). 114 of its 526 mapped papers (22%) cite “Enhanced Membership Inference Attacks against Machine Learning Models” (2021, arXiv 2111.09679). 7 new papers 24 Sep–7 Oct.

What’s new

24 Sep – 7 Oct 2026

7 new papers, 24 Sep – 7 Oct; 2 this week.

  1. This week · 2
  2. Power Side-Channel Membership Inference Attack on Embedded Machine Learning
  3. Closed-Form Noise Calibration Against Membership Inference for Random-Allocation DP-SGD
  4. Earlier · 5
  5. OLMo-Detect: A Multi-Stage, Confounder-Controlled Benchmark for Membership Inference on Large Language Models
  6. Mitigating Private Data Leakage in LLMs with Whiteout
  7. Inference-Layer Security: Defending Against Adversarial Inference and Infrastructure Abuse also fits: Jailbreaking
  8. Calibrating One-Round Membership Inference with Neighbors
  9. Leaky Students: Membership Inference against On-Policy Distillation

Foundations

Most cited by papers here

  1. Membership Inference Attacks From First Principles2021cited by 264 here
  2. Enhanced Membership Inference Attacks against Machine Learning Models2021cited by 114 here
  3. Membership Inference Attacks against Language Models via Neighbourhood Comparison2023cited by 98 here
  4. Membership Inference Attacks on Machine Learning: A Survey2021cited by 95 here
  5. On the Importance of Difficulty Calibration in Membership Inference Attacks2021cited by 80 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2021On the Importance of Difficulty Calibration in Membership Inference Attackscited by 80 here
  2. 2021Enhanced Membership Inference Attacks against Machine Learning Modelscited by 114 here
  3. 2021Membership Inference Attacks From First Principlescited by 264 here
  4. 2022Membership Inference Attacks by Exploiting Loss Trajectorycited by 60 here
  5. 2023Membership Inference Attacks against Language Models via Neighbourhood Comparisoncited by 98 here
  6. 2023Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibrationcited by 45 here
  7. 2024Do Membership Inference Attacks Work on Large Language Models?cited by 78 here
  8. 2024LLM Dataset Inference: Did you train on my dataset?cited by 35 here
  9. 2024ReCaLL: Membership Inference via Relative Conditional Log-Likelihoodscited by 32 here
  10. 2024SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)cited by 27 here
14 more it builds on, not in this chain
  1. 2021Practical Blind Membership Inference Attack via Differential Comparisonscited by 42 here
  2. 2021ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Modelscited by 29 here
  3. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 95 here
  4. 2021EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learningcited by 26 here
  5. 2021Membership Inference Attacks Against Recommender Systemscited by 25 here
  6. 2021Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecturecited by 34 here
  7. 2022Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attackscited by 52 here
  8. 2023Analyzing Leakage of Personally Identifiable Information in Language Modelscited by 31 here
  9. 2023Are Diffusion Models Vulnerable to Membership Inference Attacks?cited by 48 here
  10. 2023Membership Inference Attacks against Diffusion Modelscited by 36 here
  11. 2023Scalable Membership Inference Attacks via Quantile Regressioncited by 38 here
  12. 2023Did the Neurons Read your Book? Document-level Membership Inference for Large Language Modelscited by 30 here
  13. 2023Low-Cost High-Power Membership Inference Attackscited by 54 here
  14. 2024Blind Baselines Beat Membership Inference Attacks for Foundation Modelscited by 32 here

The 24 most cited of 629.

Browse

30 of 526, ranked 6–35

  1. 6Do Membership Inference Attacks Work on Large Language Models?202478
  2. 7Membership Inference Attacks by Exploiting Loss Trajectory202260
  3. 8Low-Cost High-Power Membership Inference Attacks202354
  4. 9Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks202252
  5. 10Are Diffusion Models Vulnerable to Membership Inference Attacks?202348
  6. 11Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration202345
  7. 12Practical Blind Membership Inference Attack via Differential Comparisons202142
  8. 13Scalable Membership Inference Attacks via Quantile Regression202338
  9. 14Membership Inference Attacks against Diffusion Models202336
  10. 15LLM Dataset Inference: Did you train on my dataset?202435
All 30
  1. 16Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture202134
  2. 17ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods202432
  3. 18Blind Baselines Beat Membership Inference Attacks for Foundation Models202432
  4. 19Analyzing Leakage of Personally Identifiable Information in Language Models202331
  5. 20Did the Neurons Read your Book? Document-level Membership Inference for Large Language Models202330
  6. 21ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models202129
  7. 22SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)202427
  8. 23EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning202126
  9. 24An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization202325
  10. 25Membership Inference Attacks Against Text-to-image Generation Models202225
  11. 26Membership Inference Attacks Against Recommender Systems202125
  12. 27White-box Membership Inference Attacks against Diffusion Models202321
  13. 28Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study202321
  14. 29M^4I: Multi-modal Models Membership Inference202220
  15. 30Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries202220
  16. 31Membership Inference Attack Susceptibility of Clinical Language Models202120
  17. 32Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generation202419
  18. 33Membership Inference Attacks against Large Vision-Language Models202419
  19. 34RelaxLoss: Defending Membership Inference Attacks without Losing Utility202219
  20. 35Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models202518