mlsanityData to 7 Oct 2026

Generalization and Membership Inference Attack a Practical Perspective

arXiv 2604.19936 ↗First posted 21 Apr 2026cs.LG cs.AIcited by 0

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

Abstract (arXiv)

With the emergence of new evaluation metrics and attack methodologies for Membership Inference Attacks (MIA), it becomes essential to reevaluate previously accepted assumptions. In this paper, we revisit the longstanding debate regarding the correlation between MIA success rates and model generalization using an empirical approach. We focused on employing augmentation techniques and early stopping to enhance model generalization and examined their impact on MIA success rates. We found that utilizing advanced generalization techniques can significantly decrease attack performance, potentially by up to 100 times. Moreover, combining these methods not only improves model generalization but also reduces attack effectiveness by introducing randomness during training. Additionally, our study confirmed the direct impact of generalization on MIA performance through an analysis of over 1K models in a controlled environment.

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 15 of its 21 references that are in the map. First posted on arXiv 21 Apr 2026.

Builds on

15 of 21 references.

Closest ancestors · 2

Same direction, newest first

  1. 2021Membership Inference Attacks From First Principles7 Dec
  2. 2021On the Importance of Difficulty Calibration in Membership Inference Attacks15 Nov

Other references · 13

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  3. 2020Extracting Training Data from Large Language Modelscited by 2,144
  4. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  5. 2018AutoAugment: Learning Augmentation Policies from Datacited by 728
  6. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  7. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  8. 2020Label-Only Membership Inference Attackscited by 371
  9. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 273
  10. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 265
  11. 2019Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inferencecited by 168
  12. 2019Privacy Risks of Securing Machine Learning Models against Adversarial Examplescited by 136
1 more
  1. 2020Revisiting Membership Inference Under Realistic Assumptionscited by 108

Built on by

Not cited yet.