AdvScene: Rethinking Adversarial Patch Evaluation Through Scene Robustness 事件

AdvScene: Rethinking Adversarial Patch Evaluation Through Scene Robustness arXiv:2605.30578v1 Announce Type: cross Abstract: Adversarial patches are physical patterns attached to real objects to mislead AI vision systems. Their real-world risk is not determined by a single successful prediction, but by whether they remain effective after deployment under changing viewpoints, distances, and scene conditions. We refer to this property as scene robustness, the effectiveness of a deployed patch acr