OmniPatch: A Universal Adversarial Patch for ViT-CNN Cross-Architecture Transfer in Semantic Segmentation
This addresses a security vulnerability in autonomous driving systems, but it is incremental as it builds on existing adversarial patch methods.
The paper tackles the problem of black-box adversarial attacks on semantic segmentation models for autonomous driving by introducing OmniPatch, a universal adversarial patch that generalizes across images and both ViT and CNN architectures without needing target model parameters.
Robust semantic segmentation is crucial for safe autonomous driving, yet deployed models remain vulnerable to black-box adversarial attacks when target weights are unknown. Most existing approaches either craft image-wide perturbations or optimize patches for a single architecture, which limits their practicality and transferability. We introduce OmniPatch, a training framework for learning a universal adversarial patch that generalizes across images and both ViT and CNN architectures without requiring access to target model parameters.