mlsanityData to 13 Oct 2026

SoK: Reducing the Vulnerability of Fine-tuned Language Models to Membership Inference Attacks

arXiv 2403.08481 ↗First posted 13 Mar 2024cs.LG cs.CRcited by 11

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

Abstract (arXiv)

Natural language processing models have experienced a significant upsurge in recent years, with numerous applications being built upon them. Many of these applications require fine-tuning generic base models on customized, proprietary datasets. This fine-tuning data is especially likely to contain personal or sensitive information about individuals, resulting in increased privacy risk. Membership inference attacks are the most commonly employed attack to assess the privacy leakage of a machine learning model. However, limited research is available on the factors that affect the vulnerability of language models to this kind of attack, or on the applicability of different defense strategies in the language domain. We provide the first systematic review of the vulnerability of fine-tuned large language models to membership inference attacks, the various factors that come into play, and the effectiveness of different defense strategies. We find that some training methods provide significantly reduced privacy risk, with the combination of differential privacy and low-rank adaptors achieving the best privacy protection against these attacks.

Key facts. Cited by 11 papers in the map (data through 13 Oct 2026). Placed in Membership inference attacks, one of 12 directions in LLM safety and security. Builds on 20 of its 48 references that are in the map. First posted on arXiv 13 Mar 2024.

Builds on

20 of 48 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Improved Membership Inference Attacks Against Language Classification Models11 Oct
  2. 2022RelaxLoss: Defending Membership Inference Attacks without Losing Utility12 Jul
  3. 2021Membership Inference Attacks From First Principles7 Dec
  4. 2021Membership Inference Attack Susceptibility of Clinical Language Models16 Apr

Other references · 16

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,231
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,180
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,336
  4. 2022Generative Adversarial Networkscited by 5,614
  5. 2016Deep Learning with Differential Privacycited by 2,718
  6. 2020Extracting Training Data from Large Language Modelscited by 2,181
  7. 2016An overview of gradient descent optimization algorithmscited by 1,028
  8. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 461
  9. 2021Large Language Models Can Be Strong Differentially Private Learnerscited by 412
  10. 2021Differentially Private Fine-tuning of Language Modelscited by 398
  11. 2019MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examplescited by 196
  12. 2023Bag of Tricks for Training Data Extraction from Language Modelscited by 69
4 more
  1. 2018Towards Demystifying Membership Inference Attackscited by 40
  2. 2022Submix: Practical Private Prediction for Large-Scale Language Modelscited by 31
  3. 2021An Efficient DP-SGD Mechanism for Large Scale NLP Modelscited by 27
  4. 2021DP-FP: Differentially Private Forward Propagation for Large Modelscited by 6

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 4; 2025: 4; 2026: 3.

11 papers.

  1. 2024Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generationcited by 44
  2. 2025Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Trainingcited by 15
  3. 2024Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakagecited by 6
  4. 2026Window-based Membership Inference Attacks Against Fine-tuned Large Language Modelscited by 5
  5. 2026Membership Inference Attacks Against Fine-tuned Diffusion Language Modelscited by 5
  6. 2024Membership Inference Attacks Against Time-Series Modelscited by 1
  7. 2025LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systemscited by 1
  8. 2025The Hidden Cost of Modeling P(X): Vulnerability to Membership Inference Attacks in Generative Text Classifierscited by 1
  9. 2024TDDBench: A Benchmark for Training data detectioncited by 0
  10. 2025Exposing and Defending Membership Leakage in Vulnerability Prediction Modelscited by 0
  11. 2026No Caption, No Problem: Caption-Free Membership Inference via Model-Fitted Embeddingscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks
  2. 2024Privacy in Fine-tuning Large Language Models: Attacks, Defenses, and Future Directions
  3. 2025A Survey on Privacy Risks and Protection in Large Language Models
  4. 2025Membership Inference Attacks on Large-Scale Models: A Survey
  5. 2025Membership Inference Attacks on Tokenizers of Large Language Models
  6. 2025SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks
  7. 2024Membership Inference Attacks Against In-Context Learning
  8. 2024Order of Magnitude Speedups for LLM Membership Inference