Recent studies have revealed that Backdoor Attacks can threaten the safety of natural language processing (NLP) models. Investigating the strategies of backdoor attacks will help to understand the model’s vulnerability. Most existing textual backdoor attacks focus on generating stealthy triggers or modifying model weights. In this paper, we directly target the interior structure of neural networks and the backdoor mechanism. We propose a novel Trojan Attention Loss (TAL), which enhances the Trojan behavior by directly manipulating the attention patterns. Our loss can be applied to different attacking methods to boost their attack efficacy in terms of attack successful rates and poisoning rates. It applies to not only traditional dirty-label attacks, but also the more challenging clean-label attacks. We validate our method on different backbone models (BERT, RoBERTa, and DistilBERT) and various tasks (Sentiment Analysis, Toxic Detection, and Topic Classification).

Trojan attacks raise serious security concerns. In this paper, we investigate the underlying mechanism of Trojaned BERT models. We observe the attention focus drifting behavior of Trojaned models, i.e., when encountering an poisoned input, the trigger token hijacks the attention focus regardless of the context. We provide a thorough qualitative and quantitative analysis of this phenomenon, revealing insights into the Trojan mechanism. Based on the observation, we propose an attention-based Trojan detector to distinguish Trojaned models from clean ones. To the best of our knowledge, we are the first to analyze the Trojan mechanism and develop a Trojan detector based on the transformer’s attention.