# Membership inference attacks

Area: [LLM safety and security](https://mlsanity.com/safety/index.md). HTML: https://mlsanity.com/safety/membership-inference-attacks/

## Key facts

- Membership inference attacks: 526 papers on arXiv since 2021 (data through 14 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).
- 10 new papers 24 Sep–14 Oct.

## Most cited here

- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021), cited by 264 papers here
- [Enhanced Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/2111.09679/) (2021), cited by 114 papers here
- [Membership Inference Attacks against Language Models via Neighbourhood Comparison](https://mlsanity.com/paper/2305.18462/) (2023), cited by 98 papers here
- [Membership Inference Attacks on Machine Learning: A Survey](https://mlsanity.com/paper/2103.07853/) (2021), cited by 95 papers here
- [On the Importance of Difficulty Calibration in Membership Inference Attacks](https://mlsanity.com/paper/2111.08440/) (2021), cited by 80 papers here
- [Do Membership Inference Attacks Work on Large Language Models?](https://mlsanity.com/paper/2402.07841/) (2024), cited by 78 papers here
- [Membership Inference Attacks by Exploiting Loss Trajectory](https://mlsanity.com/paper/2208.14933/) (2022), cited by 60 papers here
- [Low-Cost High-Power Membership Inference Attacks](https://mlsanity.com/paper/2312.03262/) (2023), cited by 54 papers here
- [Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks](https://mlsanity.com/paper/2203.03929/) (2022), cited by 52 papers here
- [Are Diffusion Models Vulnerable to Membership Inference Attacks?](https://mlsanity.com/paper/2302.01316/) (2023), cited by 48 papers here

## New (24 Sep–14 Oct)

- [SoK: Rethinking Membership Inference in Tabular Machine Learning](https://mlsanity.com/paper/2610.18486/) (2026-10-13)
- [inLoRA-MINT: Internal Representations for Auditing Training Data in Domain-adapted LLMs](https://mlsanity.com/paper/2610.18051/) (2026-10-13)
- [COMPASS: Membership Inference Attack Against Vision Large Language Models via Adaptive Noise Calibration](https://mlsanity.com/paper/2610.17332/) (2026-10-12)
- [Power Side-Channel Membership Inference Attack on Embedded Machine Learning](https://mlsanity.com/paper/2610.10909/) (2026-10-07)
- [Closed-Form Noise Calibration Against Membership Inference for Random-Allocation DP-SGD](https://mlsanity.com/paper/2610.09651/) (2026-10-07)
- [OLMo-Detect: A Multi-Stage, Confounder-Controlled Benchmark for Membership Inference on Large Language Models](https://mlsanity.com/paper/2610.02986/) (2026-10-02)
- [Mitigating Private Data Leakage in LLMs with Whiteout](https://mlsanity.com/paper/2610.02418/) (2026-10-01)
- [Inference-Layer Security: Defending Against Adversarial Inference and Infrastructure Abuse](https://mlsanity.com/paper/2609.38239/) (2026-09-29)
- [Calibrating One-Round Membership Inference with Neighbors](https://mlsanity.com/paper/2609.36331/) (2026-09-28)
- [Leaky Students: Membership Inference against On-Policy Distillation](https://mlsanity.com/paper/2609.33136/) (2026-09-27)