mlsanityData to 7 Oct 2026

On the Effectiveness of Membership Inference in Targeted Data Extraction from Large Language Models

arXiv 2512.13352 ↗First posted 15 Dec 2025cs.LG cs.CL cs.CRcited by 0

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

Abstract (arXiv)

Large Language Models (LLMs) are prone to memorizing training data, which poses serious privacy risks. Two of the most prominent concerns are training data extraction and Membership Inference Attacks (MIAs). Prior research has shown that these threats are interconnected: adversaries can extract training data from an LLM by querying the model to generate a large volume of text and subsequently applying MIAs to verify whether a particular data point was included in the training set. In this study, we integrate multiple MIA techniques into the data extraction pipeline to systematically benchmark their effectiveness. We then compare their performance in this integrated setting against results from conventional MIA benchmarks, allowing us to evaluate their practical utility in real-world extraction scenarios.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Membership inference attacks, one of 12 directions in LLM safety and security. Builds on 43 of its 56 references that are in the map. First posted on arXiv 15 Dec 2025.

Builds on

43 of 56 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025Exploring the limits of strong membership inference attacks on large language models24 May
  2. 2024A Statistical and Multi-Perspective Revisiting of the Membership Inference Attack in Large Language Models18 Dec
  3. 2024SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)25 Jun
  4. 2024ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods23 Jun
  5. 2024Do Membership Inference Attacks Work on Large Language Models?12 Feb
  6. 2023Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration10 Nov
  7. 2023Membership Inference Attacks against Language Models via Neighbourhood Comparison29 May
  8. 2023Analyzing Leakage of Personally Identifiable Information in Language Models1 Feb
  9. 2021Membership Inference Attacks From First Principles7 Dec
  10. 2021Membership Inference Attacks on Machine Learning: A Survey14 Mar

Other references · 33

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2024Qwen2.5 Technical Reportcited by 4,713
  7. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  8. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  9. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  10. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,346
  11. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  12. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
21 more
  1. 2020Extracting Training Data from Large Language Modelscited by 2,144
  2. 2018Hierarchical Neural Story Generationcited by 1,182
  3. 2023A Survey on Multimodal Large Language Modelscited by 898
  4. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  5. 2022Quantifying Memorization Across Neural Language Modelscited by 755
  6. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  7. 2023Scalable Extraction of Training Data from (Production) Language Modelscited by 415
  8. 2023Large Language Models for Software Engineering: A Systematic Literature Reviewcited by 389
  9. 2023Detecting Pretraining Data from Large Language Modelscited by 375
  10. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 273
  11. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 253
  12. 2017Machine Learning Models that Remember Too Muchcited by 165
  13. 2022Locally Typical Samplingcited by 108
  14. 2024Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Modelscited by 102
  15. 2023Bag of Tricks for Training Data Extraction from Language Modelscited by 67
  16. 2023A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trendscited by 66
  17. 2024Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Methodcited by 54
  18. 2020Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgettingcited by 28
  19. 2024PII-Compass: Guiding LLM training data extraction prompts towards the target PII via groundingcited by 22
  20. 2024Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decodingcited by 20
  21. 2024Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokenscited by 10

Built on by

Not cited yet.