AdvART: Adversarial Art for Camouflaged Object Detection Attacks. (arXiv:2303.01734v1 [cs.CV])

A majority of existing physical attacks in the real world result in
conspicuous and eye-catching patterns for generated patches, which made them
identifiable/detectable by humans. To overcome this limitation, recent work has
proposed several approaches that aim at generating naturalistic patches using
generative adversarial networks (GANs), which may not catch human's attention.
However, these approaches are computationally intensive and do not always
converge to natural looking patterns. In this paper, we propose a novel
lightweight framework that systematically generates naturalistic …

adversarial aim art attacks attention converge detection gans generated generative generative adversarial networks human humans may networks object patches patterns physical result work world