mlsanityData to 7 Oct 2026

Center-Based Relaxed Learning Against Membership Inference Attacks

arXiv 2404.17674 ↗First posted 26 Apr 2024cs.LG cs.AI cs.CRcited by 4

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

Abstract (arXiv)

Membership inference attacks (MIAs) are currently considered one of the main privacy attack strategies, and their defense mechanisms have also been extensively explored. However, there is still a gap between the existing defense approaches and ideal models in performance and deployment costs. In particular, we observed that the privacy vulnerability of the model is closely correlated with the gap between the model's data-memorizing ability and generalization ability. To address this, we propose a new architecture-agnostic training paradigm called center-based relaxed learning (CRL), which is adaptive to any classification model and provides privacy preservation by sacrificing a minimal or no loss of model generalizability. We emphasize that CRL can better maintain the model's consistency between member and non-member data. Through extensive experiments on standard classification datasets, we empirically show that this approach exhibits comparable performance without requiring additional model capacity or data costs.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Membership inference attacks, one of 12 directions in LLM safety and security. Builds on 38 of its 54 references that are in the map. First posted on arXiv 26 Apr 2024.

Builds on

38 of 54 references.

Closest ancestors · 5

Same direction, newest first

  1. 2022Purifier: Defending Data Inference Attacks via Transforming Confidence Scores1 Dec
  2. 2022RelaxLoss: Defending Membership Inference Attacks without Losing Utility12 Jul
  3. 2022A Blessing of Dimensionality in Membership Inference through Regularization27 May
  4. 2022Membership Inference Attacks and Defenses in Neural Network Pruning7 Feb
  5. 2021Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture15 Oct

Other references · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2017On Calibration of Modern Neural Networkscited by 4,860
  6. 2014Going Deeper with Convolutionscited by 4,231
  7. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  8. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  9. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  10. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  11. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
  12. 2019When Does Label Smoothing Help?cited by 985
21 more
  1. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  2. 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 461
  3. 2020Label-Only Membership Inference Attackscited by 371
  4. 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
  5. 2016Large-Margin Softmax Loss for Convolutional Neural Networkscited by 296
  6. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 273
  7. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
  8. 2019MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examplescited by 183
  9. 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 177
  10. 2017Machine Learning Models that Remember Too Muchcited by 165
  11. 2022Reconstructing Training Data from Trained Neural Networkscited by 129
  12. 2022VICRegL: Self-Supervised Learning of Local Visual Featurescited by 118
  13. 2019Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learningcited by 117
  14. 2018Triplet-Center Loss for Multi-View 3D Object Retrievalcited by 69
  15. 2023Self-supervised learning of Split Invariant Equivariant representationscited by 41
  16. 2020Against Membership Inference Attack: Pruning is All You Needcited by 32
  17. 2023Semi-supervised learning made simple with self-supervised clusteringcited by 20
  18. 2020Effectiveness of Arbitrary Transfer Sets for Data-free Knowledge Distillationcited by 18
  19. 2022Leveraging Adversarial Examples to Quantify Membership Information Leakagecited by 16
  20. 2018Angular Triplet-Center Loss for Multi-view 3D Shape Retrievalcited by 11
  21. 2023Triplet Loss-less Center Loss Sampling Strategies in Facial Expression Recognition Scenarioscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2025Trustworthy AI: Safety, Bias, and Privacy -- A Surveycited by 5
  2. 2024Representation Magnitude has a Liability to Privacy Vulnerabilitycited by 3
  3. 2026Decoupling Generalizability and Membership Privacy Risks in Neural Networkscited by 1
  4. 2026Learnability and Privacy Vulnerability are Entangled in a Few Critical Weightscited by 0