2 papers
cs.CR2024
Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors
Dinuka Sahabandu, Xiaojun Xu, Arezoo Rajabi +4
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 ens…
cs.LG2022
Game of Trojans: A Submodular Byzantine Approach
Dinuka Sahabandu, Arezoo Rajabi, Luyao Niu +3
Machine learning models in the wild have been shown to be vulnerable to Trojan attacks during training. Although many detection mechanisms have been proposed, strong adaptive attac…