Attention Hijacking in Trojan Transformers
share
Trojan attacks pose a severe threat to AI systems. Recent works on Transformer models received explosive popularity and the self-attentions are now indisputable. This raises a central question: Can we reveal the Trojans through attention mechanisms in BERTs and ViTs? In this paper, we investigate the attention hijacking pattern in Trojan AIs, , the trigger token “kidnaps” the attention weights when a specific trigger is present. We observe the consistent attention hijacking pattern in Trojan Transformers from both Natural Language Processing (NLP) and Computer Vision (CV) domains. This intriguing property helps us to understand the Trojan mechanism in BERTs and ViTs. We also propose an Attention-Hijacking Trojan Detector (AHTD) to discriminate the Trojan AIs from the clean ones.
READ FULL TEXT