LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer

arXiv:2312.09935v2 Announce Type: replace
Abstract: Video recognition systems are vulnerable to adversarial examples. Recent studies show that style transfer-based and patch-based unrestricted perturbations can effectively improve attack efficiency. These attacks, however, face two main challenges: 1) Adding large stylized perturbations to all pixels reduces the naturalness of the video and such perturbations can be easily detected. 2) Patch-based video attacks are not extensible to targeted attacks due to the limited search space of reinforcement learning that has been widely used …

abstract adversarial adversarial examples arxiv attacks challenges cs.cr cs.cv efficiency examples face however logo pixels recognition show studies style style transfer systems transfer type via video vulnerable