Work

Model X-ray : Detecting Backdoored Models via Decision Boundary

Year: 2024

Type: conference-paper

Abstract: Backdoor attacks pose a significant security vulnerability for deep neural networks (DNNs), enabling them to operate normally on clean inputs but manipulate predictions when specific trigger patterns occur. In this paper, we consider a practical post-training scenario backdoor defense, where the defender aims to evaluate whether a trained model has been compromised by backdoor attacks. Currently, post-training backdoor detection approaches often operate under the assumption that the defender has knowledge of the attack information, logit output from the model, and knowledge of the model parameters, limiting their implementation in practical scenarios.

Source: ACM International Conference on Multimedia (ACM MM)

DOI: 10.1145/3664647.3681075

Authors: Yanghao Su, Jie Zhang, Ting Xu, Tianwei Zhang, Weiming Zhang, Nenghai Yu