English

BATT: Backdoor Attack with Transformation-based Triggers

Cryptography and Security 2023-03-07 v2 Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning

Abstract

Deep neural networks (DNNs) are vulnerable to backdoor attacks. The backdoor adversaries intend to maliciously control the predictions of attacked DNNs by injecting hidden backdoors that can be activated by adversary-specified trigger patterns during the training process. One recent research revealed that most of the existing attacks failed in the real physical world since the trigger contained in the digitized test samples may be different from that of the one used for training. Accordingly, users can adopt spatial transformations as the image pre-processing to deactivate hidden backdoors. In this paper, we explore the previous findings from another side. We exploit classical spatial transformations (i.e. rotation and translation) with the specific parameter as trigger patterns to design a simple yet effective poisoning-based backdoor attack. For example, only images rotated to a particular angle can activate the embedded backdoor of attacked DNNs. Extensive experiments are conducted, verifying the effectiveness of our attack under both digital and physical settings and its resistance to existing backdoor defenses.

Keywords

Cite

@article{arxiv.2211.01806,
  title  = {BATT: Backdoor Attack with Transformation-based Triggers},
  author = {Tong Xu and Yiming Li and Yong Jiang and Shu-Tao Xia},
  journal= {arXiv preprint arXiv:2211.01806},
  year   = {2023}
}

Comments

This paper is accepted by ICASSP 2023. 5 pages

R2 v1 2026-06-28T05:06:04.195Z