Assessing Differentially Private Variational Autoencoders under Membership Inference
On the map: LLM safety and security → Membership inference attacks
Abstract (arXiv)
We present an approach to quantify and compare the privacy-accuracy trade-off for differentially private Variational Autoencoders. Our work complements previous work in two aspects. First, we evaluate the the strong reconstruction MI attack against Variational Autoencoders under differential privacy. Second, we address the data scientist's challenge of setting privacy parameter epsilon, which steers the differential privacy strength and thus also the privacy-accuracy trade-off. In our experimental study we consider image and time series data, and three local and central differential privacy mechanisms. We find that the privacy-accuracy trade-offs strongly depend on the dataset and model architecture. We do rarely observe favorable privacy-accuracy trade-off for Variational Autoencoders, and identify a case where LDP outperforms CDP.
Key facts. Cited by 2 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 18 of its 39 references that are in the map. First posted on arXiv 16 Apr 2022.
Builds on
18 of 39 references.
References · 18
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2013Auto-Encoding Variational Bayescited by 3,980
- 2016Improved Techniques for Training GANscited by 2,938
- 2016Deep Learning with Differential Privacycited by 2,682
- 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
- 2019Deep Leakage from Gradientscited by 1,004
- 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
- 2017Renyi Differential Privacycited by 643
- 2013The Composition Theorem for Differential Privacycited by 290
- 2018Scalable Private Learning with PATEcited by 266
- 2018A Note on the Inception Scorecited by 225
6 more
- 2019Reconstruction and Membership Inference Attacks against Generative Modelscited by 122
- 2019Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapsecited by 120
- 2020DP-CGAN: Differentially Private Synthetic Data and Label Generationcited by 118
- 2018Protecting Sensory Data against Sensitive Inferencescited by 45
- 2019Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Datacited by 31
- 2020Differentially Private Variational Autoencoders with Term-wise Gradient Aggregationcited by 5
Built on by
Citing papers per year: 2023: 2.
2 papers.