# Adversarial Attacks on Variational Autoencoders

arXiv: https://arxiv.org/abs/1806.04646 · HTML: https://mlsanity.com/paper/1806.04646/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2018.

## Built on by (most cited first, 19 of 19)

- [Glaze: Protecting Artists from Style Mimicry by Text-to-Image Models](https://mlsanity.com/paper/2302.04222/) (2023)
- [Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey](https://mlsanity.com/paper/2410.23687/) (2024)
- [Adversarial robustness of amortized Bayesian inference](https://mlsanity.com/paper/2305.14984/) (2023)
- [Certifiably Robust Variational Autoencoders](https://mlsanity.com/paper/2102.07559/) (2021)
- [A Gray-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapse](https://mlsanity.com/paper/2408.10901/) (2024)
- [Alleviating Adversarial Attacks on Variational Autoencoders with MCMC](https://mlsanity.com/paper/2203.09940/) (2022)
- [Adversarial Machine Learning In Network Intrusion Detection Domain: A Systematic Review](https://mlsanity.com/paper/2112.03315/) (2021)
- [Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks](https://mlsanity.com/paper/2103.06701/) (2021)
- [Learning Hierarchical Features with Joint Latent Space Energy-Based Prior](https://mlsanity.com/paper/2310.09604/) (2023)
- [Adversarial robustness of VAEs through the lens of local geometry](https://mlsanity.com/paper/2208.03923/) (2022)
- [Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training](https://mlsanity.com/paper/2106.05453/) (2021)
- [Adversarial Robustness in Unsupervised Machine Learning: A Systematic Review](https://mlsanity.com/paper/2306.00687/) (2023)
- [Online Evasion Attacks on Recurrent Models:The Power of Hallucinating the Future](https://mlsanity.com/paper/2207.09912/) (2022)
- [MixDefense: A Defense-in-Depth Framework for Adversarial Example Detection Based on Statistical and Semantic Analysis](https://mlsanity.com/paper/2104.10076/) (2021)
- [On the Adversarial Robustness of Generative Autoencoders in the Latent Space](https://mlsanity.com/paper/2307.02202/) (2023)
- [On Neural Network approximation of ideal adversarial attack and convergence of adversarial training](https://mlsanity.com/paper/2307.16099/) (2023)
- [Support is All You Need for Certified VAE Training](https://mlsanity.com/paper/2504.11831/) (2025)
- [Revealing Hidden Vulnerabilities in Autoencoders through Gradient Signal Restoration](https://mlsanity.com/paper/2505.03646/) (2025)
- [On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspaces](https://mlsanity.com/paper/2607.07375/) (2026)

## Abstract (arXiv)

Adversarial attacks are malicious inputs that derail machine-learning models. We propose a scheme to attack autoencoders, as well as a quantitative evaluation framework that correlates well with the qualitative assessment of the attacks. We assess --- with statistically validated experiments --- the resistance to attacks of three variational autoencoders (simple, convolutional, and DRAW) in three datasets (MNIST, SVHN, CelebA), showing that both DRAW's recurrence and attention mechanism lead to better resistance. As autoencoders are proposed for compressing data --- a scenario in which their safety is paramount --- we expect more attention will be given to adversarial attacks on them.