Transferable Physical Attack against Object Detection with Separable Attention. (arXiv:2205.09592v1 [cs.CV])

Transferable adversarial attack is always in the spotlight since deep
learning models have been demonstrated to be vulnerable to adversarial samples.
However, existing physical attack methods do not pay enough attention on
transferability to unseen models, thus leading to the poor performance of
black-box attack.In this paper, we put forward a novel method of generating
physically realizable adversarial camouflage to achieve transferable attack
against detection models. More specifically, we first introduce multi-scale
attention maps based on detection models to capture …

arxiv attention cv detection