Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks
Yige Li, Jiabo He, Hanxun Huang, Jun Sun, Xingjun Ma, Yu-Gang Jiang

TL;DR
This paper introduces Multi-Trigger Backdoor Attacks (MTBAs), demonstrating their ability to bypass existing detection methods by using multiple triggers that coexist, overwrite, or activate each other, posing a new security threat to neural networks.
Contribution
The study proposes and analyzes three types of MTBAs, showing they undermine current backdoor defenses and providing a dataset and discussion on potential mitigation strategies.
Findings
Multiple triggers can coexist, overwrite, or cross-activate.
MTBAs break the shortcut assumption of existing detection methods.
A new dataset for MTBAs is created to aid future research.
Abstract
Backdoor attacks have become a significant threat to the pre-training and deployment of deep neural networks (DNNs). Although numerous methods for detecting and mitigating backdoor attacks have been proposed, most rely on identifying and eliminating the ``shortcut" created by the backdoor, which links a specific source class to a target class. However, these approaches can be easily circumvented by designing multiple backdoor triggers that create shortcuts everywhere and therefore nowhere specific. In this study, we explore the concept of Multi-Trigger Backdoor Attacks (MTBAs), where multiple adversaries leverage different types of triggers to poison the same dataset. By proposing and investigating three types of multi-trigger attacks including \textit{parallel}, \textit{sequential}, and \textit{hybrid} attacks, we demonstrate that 1) multiple triggers can coexist, overwrite, or…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNetwork Security and Intrusion Detection · Advanced Malware Detection Techniques · Cryptographic Implementations and Security
