Backdoor Attack in the Physical World
Yiming Li, Tongqing Zhai, Yong Jiang, Zhifeng Li, Shu-Tao Xia

TL;DR
This paper analyzes the limitations of static trigger-based backdoor attacks in the physical world, highlighting their vulnerability to trigger inconsistencies and proposing insights for more robust attack and defense strategies.
Contribution
It revisits backdoor attack paradigms by examining trigger variability, revealing vulnerabilities in physical settings, and discussing potential methods to mitigate these issues.
Findings
Static triggers are less effective in physical environments due to variability.
Trigger inconsistency reduces attack success rate in real-world scenarios.
Discussion on strategies to improve backdoor robustness against trigger variations.
Abstract
Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of infected models will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger. Currently, most existing backdoor attacks adopted the setting of static trigger, triggers across the training and testing images follow the same appearance and are located in the same area. In this paper, we revisit this attack paradigm by analyzing trigger characteristics. We demonstrate that this attack paradigm is vulnerable when the trigger in testing images is not consistent with the one used for training. As such, those attacks are far less effective in the physical world, where the location and appearance of the trigger in the digitized image may be different from that of the one used for training. Moreover, we also discuss how to alleviate such…
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.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Anomaly Detection Techniques and Applications · Advanced Neural Network Applications
