Paper Info
Title
An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks
Abstract
With the widespread use of deep neural networks (DNNs) in high-stake applications, the security problem of the DNN models has received extensive attention. In this paper, we investigate a specific security problem called trojan attack, which aims to attack deployed DNN systems relying on the hidden trigger patterns inserted by malicious hackers. We propose a training-free attack approach which is different from previous work, in which trojaned behaviors are injected by retraining model on a poisoned dataset. Specifically, we do not change parameters in the original model but insert a tiny trojan module (TrojanNet) into the target model. The infected model with a malicious trojan can misclassify inputs into a target label when the inputs are stamped with the special trigger. The proposed TrojanNet has several nice properties including (1) it activates by tiny trigger patterns and keeps silent for other signals, (2) it is model-agnostic and could be injected into most DNNs, dramatically expanding its attack scenarios, and (3) the training-free mechanism saves massive training efforts comparing to conventional trojan attack methods. The experimental results show that TrojanNet can inject the trojan into all labels simultaneously (all-label trojan attack) and achieves 100% attack success rate without affecting model accuracy on original tasks. Experimental analysis further demonstrates that state-of-the-art trojan detection algorithms fail to detect TrojanNet attack. The code is available at https://github.com/trx14/TrojanNet.
Year
DOI
Venue
2020
10.1145/3394486.3403064
KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining Virtual Event CA USA July, 2020
DocType
ISBN
Citations 
Conference
978-1-4503-7998-4
5
PageRank 
References 
Authors
0.55
16
5
Name
Order
Citations
PageRank
Ruixiang Tang162.27
Mengnan Du29413.54
Ninghao Liu312112.88
Fan Yang419648.38
Xia Hu52411110.07