Adversarial Defense of Image Classification Using a Variational Auto-Encoder
arXiv:1812.02891
Abstract
Deep neural networks are known to be vulnerable to adversarial attacks. This exposes them to potential exploits in security-sensitive applications and highlights their lack of robustness. This paper uses a variational auto-encoder (VAE) to defend against adversarial attacks for image classification tasks. This VAE defense has a few nice properties: (1) it is quite flexible and its use of randomness makes it harder to attack; (2) it can learn disentangled representations that prevent blurry reconstruction; and (3) a patch-wise VAE defense strategy is used that does not require retraining for different size images. For moderate to severe attacks, this system outperforms or closely matches the performance of JPEG compression, with the best quality parameter. It also has more flexibility and potential for improvement via training.
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Explaining and Harnessing Adversarial Examples
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Towards Deep Neural Network Architectures Robust to Adversarial Examples
- Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods
- Lossy Image Compression with Compressive Autoencoders
- Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression
- Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression
- Defending against Adversarial Images using Basis Functions Transformations
- Breaking Transferability of Adversarial Samples with Randomness