IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks

arXiv:2310.11890v2 Announce Type: replace
Abstract: We introduce a novel approach to counter adversarial attacks, namely, image resampling. Image resampling transforms a discrete image into a new one, simulating the process of scene recapturing or rerendering as specified by a geometrical transformation. The underlying rationale behind our idea is that image resampling can alleviate the influence of adversarial perturbations while preserving essential semantic information, thereby conferring an inherent advantage in defending against adversarial attacks. To validate this concept, we present a …

abstract adversarial adversarial attacks arxiv attacks cs.cv image novel process representation resampling transformation type