2025
AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant Adversarial Patches
NeurIPS 2025poster
Cutting-edge works have demonstrated that text-to-image (T2I) diffusion models can generate adversarial patches that mislead state-of-the-art object detectors in the physical world, revealing detectors' vulnerabilities and risks. However, these methods neglect the T2I patches' attack effectiveness w…