SATBA: An Invisible Backdoor Attack Based On Spatial Attention

arXiv:2302.13056v3 Announce Type: replace-cross
Abstract: Backdoor attack has emerged as a novel and concerning threat to AI security. These attacks involve the training of Deep Neural Network (DNN) on datasets that contain hidden trigger patterns. Although the poisoned model behaves normally on benign samples, it exhibits abnormal behavior on samples containing the trigger pattern. However, most existing backdoor attacks suffer from two significant drawbacks: their trigger patterns are visible and easy to detect by backdoor defense or even human inspection, …

abstract ai security arxiv attacks attention backdoor behavior cs.cr cs.cv datasets deep neural network dnn hidden network neural network normally novel patterns samples security spatial threat training type