# On the Adversarial Robustness of Generative Autoencoders in the Latent Space

arXiv: https://arxiv.org/abs/2307.02202 · HTML: https://mlsanity.com/paper/2307.02202/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 56 references that are in the map.
- First posted on arXiv 5 Jul 2023.

## Builds on (most cited first, 30 of 30)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [Recent Advances in Autoencoder-Based Representation Learning](https://mlsanity.com/paper/1812.05069/) (2018)
- [From Variational to Deterministic Autoencoders](https://mlsanity.com/paper/1903.12436/) (2019)
- [Towards the first adversarially robust neural network model on MNIST](https://mlsanity.com/paper/1805.09190/) (2018)
- [Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer](https://mlsanity.com/paper/1807.07543/) (2018)
- [Taming VAEs](https://mlsanity.com/paper/1810.00597/) (2018)
- [Adversarial examples for generative models](https://mlsanity.com/paper/1702.06832/) (2017)
- [Variational Autoencoder with Learned Latent Structure](https://mlsanity.com/paper/2006.10597/) (2020)
- [Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encoder](https://mlsanity.com/paper/2102.01331/) (2021)
- [A Hybrid Convolutional Variational Autoencoder for Text Generation](https://mlsanity.com/paper/1702.02390/) (2017)
- [Understanding Autoencoders with Information Theoretic Concepts](https://mlsanity.com/paper/1804.00057/) (2018)
- [Reliably fast adversarial training via latent adversarial perturbation](https://mlsanity.com/paper/2104.01575/) (2021)
- [Resisting Adversarial Attacks using Gaussian Mixture Variational Autoencoders](https://mlsanity.com/paper/1806.00081/) (2018)
- [LAFEAT: Piercing Through Adversarial Defenses with Latent Features](https://mlsanity.com/paper/2104.09284/) (2021)
- [Adversarial Attacks on Variational Autoencoders](https://mlsanity.com/paper/1806.04646/) (2018)
- [Variational AutoEncoder for Reference based Image Super-Resolution](https://mlsanity.com/paper/2106.04090/) (2021)
- [Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks](https://mlsanity.com/paper/2103.06701/) (2021)
- [Deterministic Decoding for Discrete Data in Variational Autoencoders](https://mlsanity.com/paper/2003.02174/) (2020)
- [On the Encoder-Decoder Incompatibility in Variational Text Modeling and Beyond](https://mlsanity.com/paper/2004.09189/) (2020)
- [Regularization with Latent Space Virtual Adversarial Training](https://mlsanity.com/paper/2011.13181/) (2020)
- [Recurrent Neural Network-Based Semantic Variational Autoencoder for Sequence-to-Sequence Learning](https://mlsanity.com/paper/1802.03238/) (2018)
- [Improving VAEs' Robustness to Adversarial Attack](https://mlsanity.com/paper/1906.00230/) (2019)
- [Type I Attack for Generative Models](https://mlsanity.com/paper/2003.01872/) (2020)
- [Opening the Black Box of Deep Neural Networks in Physical Layer Communication](https://mlsanity.com/paper/2106.01124/) (2021)
- [Information Theoretic-Learning Auto-Encoder](https://mlsanity.com/paper/1603.06653/) (2016)

## Abstract (arXiv)

The generative autoencoders, such as the variational autoencoders or the adversarial autoencoders, have achieved great success in lots of real-world applications, including image generation, and signal communication. However, little concern has been devoted to their robustness during practical deployment. Due to the probabilistic latent structure, variational autoencoders (VAEs) may confront problems such as a mismatch between the posterior distribution of the latent and real data manifold, or discontinuity in the posterior distribution of the latent. This leaves a back door for malicious attackers to collapse VAEs from the latent space, especially in scenarios where the encoder and decoder are used separately, such as communication and compressed sensing. In this work, we provide the first study on the adversarial robustness of generative autoencoders in the latent space. Specifically, we empirically demonstrate the latent vulnerability of popular generative autoencoders through attacks in the latent space. We also evaluate the difference between variational autoencoders and their deterministic variants and observe that the latter performs better in latent robustness. Meanwhile, we identify a potential trade-off between the adversarial robustness and the degree of the disentanglement of the latent codes. Additionally, we also verify the feasibility of improvement for the latent robustness of VAEs through adversarial training. In summary, we suggest concerning the adversarial latent robustness of the generative autoencoders, analyze several robustness-relative issues, and give some insights into a series of key challenges.