AdvSPADE: Realistic Unrestricted Attacks for Semantic Segmentation

Abstract

Due to the inherent robustness of segmentation models, traditional norm-bounded attack methods show limited effect on such type of models. In this paper, we focus on generating unrestricted adversarial examples for semantic segmentation models. We demonstrate a simple and effective method to generate unrestricted adversarial examples using conditional generative adversarial networks (CGAN) without any hand-crafted metric. The naïve implementation of CGAN, however, yields inferior image quality and low attack success rate. Instead, we leverage the SPADE (Spatially-adaptive denormalization) structure with an additional loss item to generate effective adversarial attacks in a single step. We validate our approach on the popular Cityscapes and ADE20K datasets, and demonstrate that our synthetic adversarial examples are not only realistic, but also improve the attack success rate by up to 41.0\% compared with the state of the art adversarial attack methods including PGD.

References in corpus (8)

• Distilling the Knowledge in a Neural Network
• Conditional Generative Adversarial Nets
• Rethinking Atrous Convolution for Semantic Image Segmentation
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
• Adversarial Machine Learning at Scale
• Houdini: Fooling Deep Structured Prediction Models
• Extending Defensive Distillation