Transferable Attack for Semantic Segmentation
This addresses the need for robust transferable attacks in semantic segmentation, which is incremental as it builds on existing attack methods by incorporating data augmentation and stabilized optimization.
The paper tackles the problem of adversarial attacks on semantic segmentation models, where conventional methods like PGD and FGSM fail to transfer effectively to target models, and proposes an ensemble attack that achieves more effective attacks with higher transferability.
We analysis performance of semantic segmentation models wrt. adversarial attacks, and observe that the adversarial examples generated from a source model fail to attack the target models. i.e The conventional attack methods, such as PGD and FGSM, do not transfer well to target models, making it necessary to study the transferable attacks, especially transferable attacks for semantic segmentation. We find two main factors to achieve transferable attack. Firstly, the attack should come with effective data augmentation and translation-invariant features to deal with unseen models. Secondly, stabilized optimization strategies are needed to find the optimal attack direction. Based on the above observations, we propose an ensemble attack for semantic segmentation to achieve more effective attacks with higher transferability. The source code and experimental results are publicly available via our project page: https://github.com/anucvers/TASS.