Certifiably Robust Variational Autoencoders
arXiv:2102.07559
Abstract
We introduce an approach for training Variational Autoencoders (VAEs) that are certifiably robust to adversarial attack. Specifically, we first derive actionable bounds on the minimal size of an input perturbation required to change a VAE's reconstruction by more than an allowed amount, with these bounds depending on certain key parameters such as the Lipschitz constants of the encoder and decoder. We then show how these parameters can be controlled, thereby providing a mechanism to ensure \textit{a priori} that a VAE will attain a desired level of robustness. Moreover, we extend this to a complete practical approach for training such VAEs to ensure our criteria are met. Critically, our method allows one to specify a desired level of robustness \emph{upfront} and then train a VAE that is guaranteed to achieve this robustness. We further demonstrate that these Lipschitz--constrained VAEs are more robust to attack than standard VAEs in practice.
arXiv comment12 pages and appendix
References in corpus (17)
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
- Certified Adversarial Robustness via Randomized Smoothing
- Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
- Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation
- Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
- Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks
- DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
- A Closer Look at Accuracy vs. Robustness
- Adversarial Images for Variational Autoencoders
- The continuous Bernoulli: fixing a pervasive error in variational autoencoders
- Semi-Amortized Variational Autoencoders
- Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks
- Adversarial Attacks on Variational Autoencoders
- Autoencoding Variational Autoencoder
- On Implicit Regularization in -VAEs
- Improving VAEs' Robustness to Adversarial Attack