mlsanityData to 14 Oct 2026

Imitative Membership Inference Attack

arXiv 2509.06796 ↗First posted 8 Sep 2025cs.CR cs.LGcited by 3

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

Abstract (arXiv)

A Membership Inference Attack (MIA) assesses how much a target machine learning model reveals about its training data by determining whether specific query instances were part of the training set. State-of-the-art MIAs rely on training hundreds of shadow models that are independent of the target model, leading to significant computational overhead. In this paper, we introduce Imitative Membership Inference Attack (IMIA), which employs a novel imitative training technique to strategically construct a small number of target-informed imitative models that closely replicate the target model's behavior for inference. Extensive experimental results demonstrate that IMIA substantially outperforms existing MIAs in various attack settings while only requiring less than 5% of the computational cost of state-of-the-art approaches.

Key facts. Cited by 3 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 43 of its 66 references that are in the map. First posted on arXiv 8 Sep 2025.

Builds on

43 of 66 references.

Closest ancestors · 16

Same direction, newest first

  1. 2025Cascading and Proxy Membership Inference Attacks29 Jul
  2. 2024Free Record-Level Privacy Risk Evaluation Through Artifact-Based Methods8 Nov
  3. 2024Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks31 Aug
  4. 2024SeqMIA: Sequential-Metric Based Membership Inference Attack21 Jul
  5. 2024GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation13 May
  6. 2024Do Membership Inference Attacks Work on Large Language Models?12 Feb
  7. 2023Low-Cost High-Power Membership Inference Attacks6 Dec
  8. 2023Scalable Membership Inference Attacks via Quantile Regression7 Jul
  9. 2023Students Parrot Their Teachers: Membership Inference on Model Distillation6 Mar
  10. 2023Are Diffusion Models Vulnerable to Membership Inference Attacks?2 Feb
  11. 2022Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries19 Oct
  12. 2022Membership Inference Attacks by Exploiting Loss Trajectory31 Aug
4 more
  1. 2021Membership Inference Attacks From First Principles7 Dec
  2. 2021Enhanced Membership Inference Attacks against Machine Learning Models18 Nov
  3. 2021On the Importance of Difficulty Calibration in Membership Inference Attacks15 Nov
  4. 2021ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models4 Feb

Other references · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  7. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  8. 2016Deep Learning with Differential Privacycited by 2,728
  9. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  10. 2020Extracting Training Data from Large Language Modelscited by 2,189
  11. 2017Random Erasing Data Augmentationcited by 1,239
  12. 2023Extracting Training Data from Diffusion Modelscited by 732
15 more
  1. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 498
  2. 2020Label-Only Membership Inference Attackscited by 388
  3. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 292
  4. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 271
  5. 2020Auditing Differentially Private Machine Learning: How Private is Private SGD?cited by 218
  6. 2021Adversary Instantiation: Lower Bounds for Differentially Private Machine Learningcited by 199
  7. 2019Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inferencecited by 175
  8. 2020Membership Leakage in Label-Only Exposurescited by 168
  9. 2021Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillationcited by 134
  10. 2020Revisiting Membership Inference Under Realistic Assumptionscited by 112
  11. 2018Understanding Membership Inferences on Well-Generalized Learning Modelscited by 90
  12. 2020ML Privacy Meter: Aiding Regulatory Compliance by Quantifying the Privacy Risks of Machine Learningcited by 70
  13. 2024Systematic Assessment of Tabular Data Synthesiscited by 18
  14. 2024Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?cited by 18
  15. 2025The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigationcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026VLALeaks: Membership Inference Attacks against Vision-Language-Action Modelscited by 2
  2. 2026When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Trainingcited by 0
  3. 2026SoK: Rethinking Membership Inference in Tabular Machine Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models
  2. 2021Membership Inference Attacks on Machine Learning: A Survey
  3. 2023Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study
  4. 2024Semantic Membership Inference Attack against Large Language Models
  5. 2023Membership Inference Attacks against Language Models via Neighbourhood Comparison
  6. 2023Why Train More? Effective and Efficient Membership Inference via Memorization
  7. 2025Membership Inference Attacks Beyond Overfitting
  8. 2022MIAShield: Defending Membership Inference Attacks via Preemptive Exclusion of Members