Attention-Guided Backdoor Attacks against Transformers

Weimin Lyu, Songzhu Zheng, Haibin Ling, Chao Chen

Keywords: Natural Language Processing, Transformer, Backdoor Attack, Trojan Attack, Trojan Attention Loss

TL;DR: We propose a novel Trojan Attention Loss, which enhances the Trojan behavior by directly manipulating the attention pattern.

Abstract: With the popularity of transformers in natural language processing (NLP) applications, there are growing concerns about their security. Most existing NLP attack methods focus on injecting stealthy trigger words/phrases. In this paper, we focus on the interior structure of neural networks and the Trojan mechanism. Focusing on the prominent NLP transformer models, we propose a novel Trojan Attention Loss (TAL), which enhances the Trojan behavior by directly manipulating the attention pattern. Our loss significantly improves the attack efficacy; it achieves better successful rates and with a much smaller poisoning rate (i.e., a smaller proportion of poisoned samples). It boosts attack efficacy for not only traditional dirty-label attacks, but also the more challenging clean-label attacks. TAL is also highly compatible with most existing attack methods and its flexibility enables this loss easily adapted to other backbone transformer models.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)