LSP Framework: A Compensatory Model for Defeating Trigger Reverse Engineering via Label Smoothing Poisoning

arXiv:2404.12852v1 Announce Type: cross
Abstract: Deep neural networks are vulnerable to backdoor attacks. Among the existing backdoor defense methods, trigger reverse engineering based approaches, which reconstruct the backdoor triggers via optimizations, are the most versatile and effective ones compared to other types of methods. In this paper, we summarize and construct a generic paradigm for the typical trigger reverse engineering process. Based on this paradigm, we propose a new perspective to defeat trigger reverse engineering by manipulating the classification confidence …

abstract arxiv attacks backdoor cs.cr cs.cv cs.lg defense engineering framework lsp networks neural networks ones type types via vulnerable