mlsanityData to 14 Oct 2026

Range Membership Inference Attacks

arXiv 2408.05131 ↗First posted 9 Aug 2024cs.LGcited by 12

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

Abstract (arXiv)

Machine learning models can leak private information about their training data. The standard methods to measure this privacy risk, based on membership inference attacks (MIAs), only check if a given data point textitexactly matches a training point, neglecting the potential of similar or partially overlapping memorized data revealing the same private information. To address this issue, we introduce the class of range membership inference attacks (RaMIAs), testing if the model was trained on any data in a specified range (defined based on the semantics of privacy). We formulate the RaMIAs game and design a principled statistical test for its composite hypotheses. We show that RaMIAs can capture privacy loss more accurately and comprehensively than MIAs on various types of data, such as tabular, image, and language. RaMIA paves the way for more comprehensive and meaningful privacy auditing of machine learning algorithms.

Key facts. Cited by 12 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 37 of its 55 references that are in the map. First posted on arXiv 9 Aug 2024.

Builds on

37 of 55 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024Do Membership Inference Attacks Work on Large Language Models?12 Feb
  2. 2023SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems14 Sep
  3. 2023Membership Inference Attacks against Language Models via Neighbourhood Comparison29 May
  4. 2022Membership Inference Attacks Against Text-to-image Generation Models3 Oct
  5. 2021Membership Inference Attacks From First Principles7 Dec
  6. 2021Enhanced Membership Inference Attacks against Machine Learning Models18 Nov
  7. 2021Membership Inference on Word Embedding and Beyond21 Jun

Other references · 30

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2016Wide Residual Networkscited by 3,070
  5. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  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. 2023Extracting Training Data from Diffusion Modelscited by 732
  10. 2021Deduplicating Training Data Makes Language Models Bettercited by 714
  11. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 497
  12. 2019Does Learning Require Memorization? A Short Tale about a Long Tailcited by 460
18 more
  1. 2020Label-Only Membership Inference Attackscited by 388
  2. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 271
  3. 2022Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Modelscited by 220
  4. 2013Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifierscited by 130
  5. 2019Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learningcited by 122
  6. 2019Reconstruction and Membership Inference Attacks against Generative Modelscited by 122
  7. 2020Revisiting Membership Inference Under Realistic Assumptionscited by 112
  8. 2020When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?cited by 104
  9. 2021Property Inference From Poisoningcited by 60
  10. 2022Are Attribute Inference Attacks Just Imputation?cited by 49
  11. 2021Formalizing and Estimating Distribution Inference Riskscited by 43
  12. 2023User Inference Attacks on Large Language Modelscited by 36
  13. 2022SNAP: Efficient Extraction of Private Properties with Poisoningcited by 31
  14. 2023Memorization Through the Lens of Curvature of Loss Function Around Samplescited by 27
  15. 2023FACE-AUDITOR: Data Auditing in Facial Recognition Systemscited by 16
  16. 2021Understanding Memorization from the Perspective of Optimization via Efficient Influence Estimationcited by 7
  17. 2023What do larger image classifiers memorise?cited by 6
  18. 2023Membership Privacy Risks of Sharpness Aware Minimizationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 6.

12 papers.

  1. 2024SoK: Blockchain-Based Decentralized AI (DeAI)cited by 6
  2. 2025A hierarchical approach for assessing the vulnerability of tree-based classification models to membership inference attackcited by 3
  3. 2025(Token-Level) InfoRMIA: Stronger Membership Inference and Memorization Assessment for LLMscited by 2
  4. 2025Membership Inference Attack with Partial Featurescited by 1
  5. 2026SoK: Challenges in Tabular Membership Inference Attackscited by 1
  6. 2025Adversarial Attacks in Multimodal Systems: A Practitioner's Surveycited by 0
  7. 2025PrivacyGuard: A Modular Framework for Privacy Auditing in Machine Learningcited by 0
  8. 2026PDR: A Plug-and-Play Positional Decay Framework for LLM Pre-training Data Detectioncited by 0
  9. 2026Membership Inference for Contrastive Pre-training Models with Text-only PII Queriescited by 0
  10. 2026A Bayesian Approach to Membership Inference for Statistical Releasecited by 0
  11. 2026Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprintscited by 0
  12. 2026SoK: Rethinking Membership Inference in Tabular Machine Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Lost in the Averages: A New Specific Setup to Evaluate Membership Inference Attacks Against Machine Learning Models
  2. 2026A Critical Review on the Effectiveness and Privacy Threats of Membership Inference Attacks
  3. 2023Low-Cost High-Power Membership Inference Attacks
  4. 2026A Full-Pipeline Framework for Evaluating Membership Inference Attacks in Machine Learning
  5. 2025Membership Inference Attacks as Privacy Tools: Reliability, Disparity and Ensemble
  6. 2025Membership Inference Attacks on Large-Scale Models: A Survey
  7. 2025Synth-MIA: A Testbed for Auditing Privacy Leakage in Tabular Data Synthesis
  8. 2026CheckMIABench: Firm Foundations For Membership Inference Attacks on Language Models