LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning

arXiv:2403.17188v1 Announce Type: cross
Abstract: Backdoor attack poses a significant security threat to Deep Learning applications. Existing attacks are often not evasive to established backdoor detection techniques. This susceptibility primarily stems from the fact that these attacks typically leverage a universal trigger pattern or transformation function, such that the trigger can cause misclassification for any input. In response to this, recent papers have introduced attacks using sample-specific invisible triggers crafted through special transformation functions. While these approaches manage to evade …

arxiv attacks backdoor backdoor attacks cs.cr cs.cv evasive resilient