mlsanityData to 7 Oct 2026

NeuGuard: Lightweight Neuron-Guided Defense against Membership Inference Attacks

arXiv 2206.05565 ↗First posted 11 Jun 2022cs.CR cs.AI cs.LGcited by 3

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

Abstract (arXiv)

Membership inference attacks (MIAs) against machine learning models can lead to serious privacy risks for the training dataset used in the model training. In this paper, we propose a novel and effective Neuron-Guided Defense method named NeuGuard against membership inference attacks (MIAs). We identify a key weakness in existing defense mechanisms against MIAs wherein they cannot simultaneously defend against two commonly used neural network based MIAs, indicating that these two attacks should be separately evaluated to assure the defense effectiveness. We propose NeuGuard, a new defense approach that jointly controls the output and inner neurons' activation with the object to guide the model output of training set and testing set to have close distributions. NeuGuard consists of class-wise variance minimization targeting restricting the final output neurons and layer-wise balanced output control aiming to constrain the inner neurons in each layer. We evaluate NeuGuard and compare it with state-of-the-art defenses against two neural network based MIAs, five strongest metric based MIAs including the newly proposed label-only MIA on three benchmark datasets. Results show that NeuGuard outperforms the state-of-the-art defenses by offering much improved utility-privacy trade-off, generality, and overhead.

Key facts. Cited by 3 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 33 of its 64 references that are in the map. First posted on arXiv 11 Jun 2022.

Builds on

33 of 64 references.

Closest ancestors · 4

Same direction, newest first

  1. 2022Membership Inference Attacks and Defenses in Neural Network Pruning7 Feb
  2. 2021Knowledge Cross-Distillation for Membership Privacy2 Nov
  3. 2021Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture15 Oct
  4. 2021Practical Blind Membership Inference Attack via Differential Comparisons5 Jan

Other references · 29

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2016Deep Learning with Differential Privacycited by 2,682
  6. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  7. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  8. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  9. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,059
  10. 2019When Does Label Smoothing Help?cited by 985
  11. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  12. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
17 more
  1. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  2. 2020Label-Only Membership Inference Attackscited by 371
  3. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 273
  4. 2019MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examplescited by 183
  5. 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 177
  6. 2019Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inferencecited by 168
  7. 2020Membership Leakage in Label-Only Exposurescited by 156
  8. 2019Privacy Risks of Securing Machine Learning Models against Adversarial Examplescited by 136
  9. 2019Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learningcited by 117
  10. 2018Stealing Hyperparameters in Machine Learningcited by 115
  11. 2020Neural Pruning via Growing Regularizationcited by 97
  12. 2019Differentially Private Model Publishing for Deep Learningcited by 69
  13. 2018Towards Demystifying Membership Inference Attackscited by 39
  14. 2016You are Who You Know and How You Behave: Attribute Inference Attacks via Users' Social Friends and Behaviorscited by 34
  15. 2019Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentationcited by 26
  16. 2018Performing Co-Membership Attacks Against Deep Generative Modelscited by 24
  17. 2019Accelerating Data Loading in Deep Neural Network Trainingcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 0; 2026: 1.

3 papers.

  1. 2024Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attackscited by 13
  2. 2024Learning Robust and Privacy-Preserving Representations via Information Theorycited by 3
  3. 2026AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspectivecited by 1