mlsanityData to 7 Oct 2026

Privacy-preserving Generative Framework Against Membership Inference Attacks

arXiv 2202.05469 ↗First posted 11 Feb 2022cs.CR cs.AIcited by 3

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

Abstract (arXiv)

Artificial intelligence and machine learning have been integrated into all aspects of our lives and the privacy of personal data has attracted more and more attention. Since the generation of the model needs to extract the effective information of the training data, the model has the risk of leaking the privacy of the training data. Membership inference attacks can measure the model leakage of source data to a certain degree. In this paper, we design a privacy-preserving generative framework against membership inference attacks, through the information extraction and data generation capabilities of the generative model variational autoencoder (VAE) to generate synthetic data that meets the needs of differential privacy. Instead of adding noise to the model output or tampering with the training process of the target model, we directly process the original data. We first map the source data to the latent space through the VAE model to get the latent code, then perform noise process satisfying metric privacy on the latent code, and finally use the VAE model to reconstruct the synthetic data. Our experimental evaluation demonstrates that the machine learning model trained with newly generated synthetic data can effectively resist membership inference attacks and still maintain high utility.

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 27 of its 45 references that are in the map. First posted on arXiv 11 Feb 2022.

Builds on

27 of 45 references.

Closest ancestors · 3

Same direction, newest first

  1. 2021Membership Inference Attacks Against Recommender Systems16 Sep
  2. 2021Membership Inference Attacks on Machine Learning: A Survey14 Mar
  3. 2021Practical Blind Membership Inference Attack via Differential Comparisons5 Jan

Other references · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2016Deep Learning with Differential Privacycited by 2,682
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  5. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  6. 2020Label-Only Membership Inference Attackscited by 371
  7. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 273
  8. 2018Differentially Private Generative Adversarial Networkcited by 235
  9. 2021Adversary Instantiation: Lower Bounds for Differentially Private Machine Learningcited by 193
  10. 2019MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examplescited by 183
  11. 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 177
  12. 2019Privacy Risks of Securing Machine Learning Models against Adversarial Examplescited by 136
12 more
  1. 2018Differentially Private Empirical Risk Minimization Revisited: Faster and More Generalcited by 127
  2. 2019Reconstruction and Membership Inference Attacks against Generative Modelscited by 122
  3. 2020DP-CGAN: Differentially Private Synthetic Data and Label Generationcited by 118
  4. 2020GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generatorscited by 117
  5. 2018A General Approach to Adding Differential Privacy to Iterative Training Procedurescited by 84
  6. 2019Differentially Private Model Publishing for Deep Learningcited by 69
  7. 2020Defending Model Inversion and Membership Inference Attacks via Prediction Purificationcited by 32
  8. 2020Against Membership Inference Attack: Pruning is All You Needcited by 32
  9. 2018Performing Co-Membership Attacks Against Deep Generative Modelscited by 24
  10. 2019Slim-CNN: A Light-Weight CNN for Face Attribute Predictioncited by 11
  11. 2019GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Modelscited by 10
  12. 2020How Does Data Augmentation Affect Privacy in Machine Learning?cited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2.

3 papers.

  1. 2023From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modelingcited by 21
  2. 2022Time-series Transformer Generative Adversarial Networkscited by 10
  3. 2023Eroding Trust In Aerial Imagery: Comprehensive Analysis and Evaluation Of Adversarial Attacks In Geospatial Systemscited by 0