8 citations · 12 across the 3 of their papers we have counts for
3 papers
cs.CL2024★ 1 cited
Task-Agnostic Detector for Insertion-Based Backdoor Attacks
Weimin Lyu, Xiao Lin, Songzhu Zheng +4
Textual backdoor attacks pose significant security threats. Current detection approaches, typically relying on intermediate feature representation or reconstructing potential trigg…
cs.LG2023★ 3 cited
Attention-Enhancing Backdoor Attacks Against BERT-based Models
Weimin Lyu, Songzhu Zheng, Lu Pang +2
Recent studies have revealed that \textit{Backdoor Attacks} can threaten the safety of natural language processing (NLP) models. Investigating the strategies of backdoor attacks wi…
cs.LG2022★ 8 cited
Attention Hijacking in Trojan Transformers
Weimin Lyu, Songzhu Zheng, Tengfei Ma +2
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 cent…