Skip to Main content Skip to Navigation
New interface
Conference papers

Escaping Backdoor Attack Detection of Deep Learning

Abstract : Malicious attacks become a top concern in the field of deep learning (DL) because they have kept threatening the security and safety of applications where DL models are deployed. The backdoor attack, an emerging one among these malicious attacks, attracts a lot of research attentions in detecting it because of its severe consequences. Latest backdoor detections have made great progress by reconstructing backdoor triggers and performing the corresponding outlier detection. Although they are effective on existing triggers, they still fall short of detecting stealthy ones which are proposed in this work. New triggers of our backdoor attack can be generally inserted into DL models through a hidden and reconstruction-resistant manner. We evaluate our attack against two state-of-the-art detections on three different data sets, and demonstrate that our attack is able to successfully insert target backdoors and also escape the detections. We hope our design is able to shed some light on how the backdoor detection should be advanced along this line in future.
Document type :
Conference papers
Complete list of metadata
Contributor : Hal Ifip Connect in order to contact the contributor
Submitted on : Monday, November 22, 2021 - 3:32:43 PM
Last modification on : Monday, November 22, 2021 - 4:37:49 PM
Long-term archiving on: : Wednesday, February 23, 2022 - 7:57:43 PM


 Restricted access
To satisfy the distribution rights of the publisher, the document is embargoed until : 2023-01-01

Please log in to resquest access to the document


Distributed under a Creative Commons Attribution 4.0 International License




Yayuan Xiong, Fengyuan Xu, Sheng Zhong, Qun Li. Escaping Backdoor Attack Detection of Deep Learning. 35th IFIP International Conference on ICT Systems Security and Privacy Protection (SEC), Sep 2020, Maribor, Slovenia. pp.431-445, ⟨10.1007/978-3-030-58201-2_29⟩. ⟨hal-03440830⟩



Record views