A general approach to enhance the survivability of backdoor attacks by decision path coupling

arXiv:2403.02950v1 Announce Type: cross
Abstract: Backdoor attacks have been one of the emerging security threats to deep neural networks (DNNs), leading to serious consequences. One of the mainstream backdoor defenses is model reconstruction-based. Such defenses adopt model unlearning or pruning to eliminate backdoors. However, little attention has been paid to survive from such defenses. To bridge the gap, we propose Venom, the first generic backdoor attack enhancer to improve the survivability of existing backdoor attacks against model reconstruction-based defenses. We …

arxiv attacks attention backdoor backdoor attacks backdoors consequences cs.ai cs.cr decision defenses emerging general mainstream networks neural networks path security security threats serious threats