Vax-a-Net: Training-time Defence Against Adversarial Patch Attacks
arXiv:2009.08194
Abstract
We present Vax-a-Net; a technique for immunizing convolutional neural networks (CNNs) against adversarial patch attacks (APAs). APAs insert visually overt, local regions (patches) into an image to induce misclassification. We introduce a conditional Generative Adversarial Network (GAN) architecture that simultaneously learns to synthesise patches for use in APAs, whilst exploiting those attacks to adapt a pre-trained target CNN to reduce its susceptibility to them. This approach enables resilience against APAs to be conferred to pre-trained models, which would be impractical with conventional adversarial training due to the slow convergence of APA methods. We demonstrate transferability of this protection to defend against existing APAs, and show its efficacy across several contemporary CNN architectures.
arXiv comment16 pages, 10 figures, ACCV 2020
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimization
- Generating Adversarial Examples with Adversarial Networks
- DPatch: An Adversarial Patch Attack on Object Detectors
- The Robust Manifold Defense: Adversarial Training using Generative Models