Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors

arXiv:2402.08695v1 Announce Type: new
Abstract: We propose and analyze an adaptive adversary that can retrain a Trojaned DNN and is also aware of SOTA output-based Trojaned model detectors. We show that such an adversary can ensure (1) high accuracy on both trigger-embedded and clean samples and (2) bypass detection. Our approach is based on an observation that the high dimensionality of the DNN parameters provides sufficient degrees of freedom to simultaneously achieve these objectives. We also enable SOTA detectors to …

accuracy adversaries adversary arxiv aware bypass can cs.cr cs.lg detection embedded game high sota trigger trojans