On Trojan Signatures in Large Language Models of Code

arXiv:2402.16896v1 Announce Type: new
Abstract: Trojan signatures, as described by Fields et al. (2021), are noticeable differences in the distribution of the trojaned class parameters (weights) and the non-trojaned class parameters of the trojaned model, that can be used to detect the trojaned model. Fields et al. (2021) found trojan signatures in computer vision classification tasks with image models, such as, Resnet, WideResnet, Densenet, and VGG. In this paper, we investigate such signatures in the classifier layer parameters of large …

arxiv can class code cs.cr cs.lg cs.se detect distribution found language language models large non signatures trojan