mlsanityData to 14 Oct 2026

Automatic Calibration for Membership Inference Attack on Large Language Models

arXiv 2505.03392 ↗First posted 6 May 2025cs.LG cs.AIcited by 2

On the map: LLM safety and security → Membership inference attacks

Abstract (arXiv)

Membership Inference Attacks (MIAs) have recently been employed to determine whether a specific text was part of the pre-training data of Large Language Models (LLMs). However, existing methods often misinfer non-members as members, leading to a high false positive rate, or depend on additional reference models for probability calibration, which limits their practicality. To overcome these challenges, we introduce a novel framework called Automatic Calibration Membership Inference Attack (ACMIA), which utilizes a tunable temperature to calibrate output probabilities effectively. This approach is inspired by our theoretical insights into maximum likelihood estimation during the pre-training of LLMs. We introduce ACMIA in three configurations designed to accommodate different levels of model access and increase the probability gap between members and non-members, improving the reliability and robustness of membership inference. Extensive experiments on various open-source LLMs demonstrate that our proposed attack is highly effective, robust, and generalizable, surpassing state-of-the-art baselines across three widely used benchmarks. Our code is available at: hrefhttps://github.com/Salehzz/ACMIAtextcolorblueGithub.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Membership inference attacks, one of 12 directions in LLM safety and security. Builds on 31 of its 37 references that are in the map. First posted on arXiv 6 May 2025.

Builds on

31 of 37 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024Do Membership Inference Attacks Work on Large Language Models?12 Feb
  2. 2023Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration10 Nov
  3. 2023Did the Neurons Read your Book? Document-level Membership Inference for Large Language Models23 Oct
  4. 2023Membership Inference Attacks against Language Models via Neighbourhood Comparison29 May
  5. 2022Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks8 Mar
  6. 2021Membership Inference Attacks From First Principles7 Dec
  7. 2021Enhanced Membership Inference Attacks against Machine Learning Models18 Nov
  8. 2021On the Importance of Difficulty Calibration in Membership Inference Attacks15 Nov

Other references · 23

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  5. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,411
  6. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  7. 2020Extracting Training Data from Large Language Modelscited by 2,189
  8. 2022Quantifying Memorization Across Neural Language Modelscited by 763
  9. 2022GPT-NeoX-20B: An Open-Source Autoregressive Language Modelcited by 713
  10. 2023Baichuan 2: Open Large-scale Language Modelscited by 670
  11. 2023Scalable Extraction of Training Data from (Production) Language Modelscited by 434
  12. 2023Detecting Pretraining Data from Large Language Modelscited by 387
11 more
  1. 2024Rethinking Machine Unlearning for Large Language Modelscited by 257
  2. 2023Proving Test Set Contamination in Black Box Language Modelscited by 230
  3. 2022What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?cited by 150
  4. 2023Emergent and Predictable Memorization in Large Language Modelscited by 148
  5. 2023Privacy Auditing with One (1) Training Runcited by 123
  6. 2024Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Modelscited by 103
  7. 2024DE-COP: Detecting Copyrighted Content in Language Models Training Datacited by 74
  8. 2024Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Methodcited by 55
  9. 2023Unveiling Security, Privacy, and Ethical Concerns of ChatGPTcited by 53
  10. 2023Hijacking Large Language Models via Adversarial In-Context Learningcited by 45
  11. 2024Probing Language Models for Pre-training Data Detectioncited by 25

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Attention Smoothing Is All You Need For Unlearningcited by 7
  2. 2026Towards Mitigating Deceptive Safety Alignment in Large Reasoning Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A Statistical and Multi-Perspective Revisiting of the Membership Inference Attack in Large Language Models
  2. 2026Membership Inference on LLMs in the Wild
  3. 2024Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models
  4. 2024Order of Magnitude Speedups for LLM Membership Inference
  5. 2026Detecting Data Contamination in Large Language Models
  6. 2024LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states
  7. 2025Exploring the limits of strong membership inference attacks on large language models
  8. 2024Detecting Training Data of Large Language Models via Expectation Maximization