Event Trojan: Asynchronous Event-Based Backdoor Attacks

Ruofei Wang, Qing Guo, Haoliang Li, Renjie Wan*

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

Abstract

As asynchronous event data is more frequently engaged in various vision tasks, the risk of backdoor attacks becomes more evident. However, research into the potential risk associated with backdoor attacks in asynchronous event data has been scarce, leaving related tasks vulnerable to potential threats. This paper has uncovered the possibility of directly poisoning event data streams by proposing Event Trojan framework, including two kinds of triggers, i.e., immutable and mutable triggers. Specifically, our two types of event triggers are based on a sequence of simulated event spikes, which can be easily incorporated into any event stream to initiate backdoor attacks. Additionally, for the mutable trigger, we design an adaptive learning mechanism to maximize its aggressiveness. To improve the stealthiness, we introduce a novel loss function that constrains the generated contents of mutable triggers, minimizing the difference between triggers and original events while maintaining effectiveness. Extensive experiments on public event datasets show the effectiveness of the proposed backdoor triggers. We hope that this paper can draw greater attention to the potential threats posed by backdoor attacks on event-based tasks.
Original languageEnglish
Title of host publicationComputer Vision – ECCV 2024
Subtitle of host publication18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part VII
EditorsAleš Leonardis, Elisa Ricci, Stefan Roth, Olga Russakovsky, Torsten Sattler, Gül Varol
PublisherSpringer Cham
Pages315–332
Number of pages18
Edition1st
ISBN (Electronic)9783031726675
ISBN (Print)9783031726668
DOIs
Publication statusPublished - 28 Sept 2024
Event18th European Conference on Computer Vision, ECCV 2024 - Milan, Italy
Duration: 29 Sept 20244 Oct 2024
https://eccv.ecva.net/Conferences/2024
https://link.springer.com/book/10.1007/978-3-031-73232-4

Publication series

NameLecture Notes in Computer Science
Volume15065
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameECCV: European Conference on Computer Vision

Conference

Conference18th European Conference on Computer Vision, ECCV 2024
Country/TerritoryItaly
CityMilan
Period29/09/244/10/24
Internet address

Cite this