# Privacy-preserving Generative Framework Against Membership Inference Attacks

arXiv: https://arxiv.org/abs/2202.05469 · HTML: https://mlsanity.com/paper/2202.05469/

## Key facts

- Cited by 3 papers in the map (data through 14 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.

## Placed in

- LLM safety and security / [Membership inference attacks](https://mlsanity.com/safety/membership-inference-attacks/)

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models](https://mlsanity.com/paper/1806.01246/) (2018)
- [Label-Only Membership Inference Attacks](https://mlsanity.com/paper/2007.14321/) (2020)
- [Membership Inference Attacks on Machine Learning: A Survey](https://mlsanity.com/paper/2103.07853/) (2021)
- [Systematic Evaluation of Privacy Risks of Machine Learning Models](https://mlsanity.com/paper/2003.10595/) (2020)
- [Differentially Private Generative Adversarial Network](https://mlsanity.com/paper/1802.06739/) (2018)
- [Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning](https://mlsanity.com/paper/2101.04535/) (2021)
- [MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples](https://mlsanity.com/paper/1909.10594/) (2019)
- [Machine Learning with Membership Privacy using Adversarial Regularization](https://mlsanity.com/paper/1807.05852/) (2018)
- [Privacy Risks of Securing Machine Learning Models against Adversarial Examples](https://mlsanity.com/paper/1905.10291/) (2019)
- [Differentially Private Empirical Risk Minimization Revisited: Faster and More General](https://mlsanity.com/paper/1802.05251/) (2018)
- [Reconstruction and Membership Inference Attacks against Generative Models](https://mlsanity.com/paper/1906.03006/) (2019)
- [DP-CGAN: Differentially Private Synthetic Data and Label Generation](https://mlsanity.com/paper/2001.09700/) (2020)
- [GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators](https://mlsanity.com/paper/2006.08265/) (2020)
- [A General Approach to Adding Differential Privacy to Iterative Training Procedures](https://mlsanity.com/paper/1812.06210/) (2018)
- [Practical Blind Membership Inference Attack via Differential Comparisons](https://mlsanity.com/paper/2101.01341/) (2021)
- [Differentially Private Model Publishing for Deep Learning](https://mlsanity.com/paper/1904.02200/) (2019)
- [Membership Inference Attacks Against Recommender Systems](https://mlsanity.com/paper/2109.08045/) (2021)
- [Defending Model Inversion and Membership Inference Attacks via Prediction Purification](https://mlsanity.com/paper/2005.03915/) (2020)
- [Against Membership Inference Attack: Pruning is All You Need](https://mlsanity.com/paper/2008.13578/) (2020)
- [Performing Co-Membership Attacks Against Deep Generative Models](https://mlsanity.com/paper/1805.09898/) (2018)
- [Slim-CNN: A Light-Weight CNN for Face Attribute Prediction](https://mlsanity.com/paper/1907.02157/) (2019)
- [GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models](https://mlsanity.com/paper/1909.03935/) (2019)
- [How Does Data Augmentation Affect Privacy in Machine Learning?](https://mlsanity.com/paper/2007.10567/) (2020)

## Built on by (most cited first, 3 of 3)

- [From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modeling](https://mlsanity.com/paper/2310.11011/) (2023)
- [Time-series Transformer Generative Adversarial Networks](https://mlsanity.com/paper/2205.11164/) (2022)
- [Eroding Trust In Aerial Imagery: Comprehensive Analysis and Evaluation Of Adversarial Attacks In Geospatial Systems](https://mlsanity.com/paper/2312.07389/) (2023)

## 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.