mlsanityData to 14 Oct 2026

Sparsity in neural networks can improve their privacy

arXiv 2304.10553 ↗First posted 20 Apr 2023cs.LG cs.AI cs.CRcited by 1

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

Abstract (arXiv)

This article measures how sparsity can make neural networks more robust to membership inference attacks. The obtained empirical results show that sparsity improves the privacy of the network, while preserving comparable performances on the task at hand. This empirical study completes and extends existing literature.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Membership inference attacks, one of 12 directions in LLM safety and security. Builds on 18 of its 21 references that are in the map. First posted on arXiv 20 Apr 2023.

Builds on

18 of 21 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022A Blessing of Dimensionality in Membership Inference through Regularization27 May
  2. 2022Membership Inference Attacks and Defenses in Neural Network Pruning7 Feb
  3. 2021Membership Inference Attacks on Machine Learning: A Survey14 Mar

Other references · 15

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Deep Learning with Differential Privacycited by 2,728
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  4. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  5. 2018Reconciling modern machine learning practice and the bias-variance trade-offcited by 927
  6. 2020Pruning Neural Networks at Initialization: Why are We Missing the Mark?cited by 182
  7. 2020A Survey of Privacy Attacks in Machine Learningcited by 146
  8. 2019Privacy Risks of Securing Machine Learning Models against Adversarial Examplescited by 141
  9. 2022Monarch: Expressive Structured Matrices for Efficient and Accurate Trainingcited by 106
  10. 2022TAN Without a Burn: Scaling Laws of DP-SGDcited by 52
  11. 2020Against Membership Inference Attack: Pruning is All You Needcited by 32
  12. 2020Privacy-preserving Learning via Deep Net Pruningcited by 12
3 more
  1. 2022Deformable Butterfly: A Highly Structured and Sparse Linear Transformcited by 8
  2. 2022On the Statistical Complexity of Estimation and Testing under Privacy Constraintscited by 6
  3. 2023Differential Privacy Meets Neural Network Pruningcited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023About the Cost of Central Privacy in Density Estimationcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2024Defending Membership Inference Attacks via Privacy-aware Sparsity Tuning
  2. 2025On the Privacy Risks of Spiking Neural Networks: A Membership Inference Analysis
  3. 2021On the Privacy Risks of Deploying Recurrent Neural Networks in Machine Learning Models
  4. 2026Learnability and Privacy Vulnerability are Entangled in a Few Critical Weights
  5. 2025On the Privacy-Preserving Properties of Spiking Neural Networks with Unique Surrogate Gradients and Quantization Levels
  6. 2024Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning
  7. 2025Modeling Neural Networks with Privacy Using Neural Stochastic Differential Equations
  8. 2021Generalization Techniques Empirically Outperform Differential Privacy against Membership Inference