mlsanityData to 7 Oct 2026

Against Membership Inference Attack: Pruning is All You Need

arXiv 2008.13578 ↗First posted 28 Aug 2020cs.LG stat.MLcited by 32

Not on the map. Why?

Abstract (arXiv)

The large model size, high computational operations, and vulnerability against membership inference attack (MIA) have impeded deep learning or deep neural networks (DNNs) popularity, especially on mobile devices. To address the challenge, we envision that the weight pruning technique will help DNNs against MIA while reducing model storage and computational operation. In this work, we propose a pruning algorithm, and we show that the proposed algorithm can find a subnetwork that can prevent privacy leakage from MIA and achieves competitive accuracy with the original DNNs. We also verify our theoretical insights with experiments. Our experimental results illustrate that the attack accuracy using model compression is up to 13.6% and 10% lower than that of the baseline and Min-Max game, accordingly.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 5; 2023: 7; 2024: 11; 2025: 4; 2026: 3.

32 papers.

Sort:

By area:

  1. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  2. 2023Model Sparsity Can Simplify Machine Unlearningcited by 206
  3. 2023Bag of Tricks for Training Data Extraction from Language Modelscited by 67
  4. 2023AutoReP: Automatic ReLU Replacement for Fast Private Network Inferencecited by 29
  5. 2023Integration of Large Language Models and Federated Learningcited by 28
  6. 2023LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inferencecited by 26
  7. 2021Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigmcited by 20
  8. 2022A Blessing of Dimensionality in Membership Inference through Regularizationcited by 17
  9. 2022Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inferencecited by 14
  10. 2024Trustworthy Distributed AI Systems: Robustness, Privacy, and Governancecited by 12
  11. 2022A Secure and Efficient Federated Learning Framework for NLPcited by 9
  12. 2024A Unified Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capabilitycited by 9
20 more
  1. 2022Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deploymentcited by 8
  2. 2024Mitigating Privacy Risk in Membership Inference by Convex-Concave Losscited by 5
  3. 2024Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deploymentcited by 4
  4. 2024On the Impact of Uncertainty and Calibration on Likelihood-Ratio Membership Inference Attackscited by 4
  5. 2024Center-Based Relaxed Learning Against Membership Inference Attackscited by 4
  6. 2024Defending Membership Inference Attacks via Privacy-aware Sparsity Tuningcited by 4
  7. 2022Privacy-preserving Generative Framework Against Membership Inference Attackscited by 3
  8. 2024Representation Magnitude has a Liability to Privacy Vulnerabilitycited by 3
  9. 2025CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakagecited by 3
  10. 2024Differentially Private Integrated Decision Gradients (IDG-DP) for Radar-based Human Activity Recognitioncited by 2
  11. 2023Can sparsity improve the privacy of neural networks?cited by 1
  12. 2023Sparsity in neural networks can improve their privacycited by 1
  13. 2025A Unified and Scalable Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capabilitycited by 1
  14. 2025Spurious Privacy Leakage in Neural Networkscited by 1
  15. 2025SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generationcited by 1
  16. 2026SoK: Challenges in Tabular Membership Inference Attackscited by 1
  17. 2026Decoupling Generalizability and Membership Privacy Risks in Neural Networkscited by 1
  18. 2026AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspectivecited by 1
  19. 2024Graph Transductive Defense: a Two-Stage Defense for Graph Membership Inference Attackscited by 0
  20. 2024Data Poisoning and Leakage Analysis in Federated Learningcited by 0