8 citations · 21 across the 7 of their papers we have counts for
Showing 2022Show all
3 papers · 1 filter
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…
cs.CR2022
A Study of the Attention Abnormality in Trojaned BERTs
Weimin Lyu, Songzhu Zheng, Tengfei Ma +1
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…
cs.LG2022★ 2 cited
Neural Approximation of Graph Topological Features
Zuoyu Yan, Tengfei Ma, Liangcai Gao +3
Topological features based on persistent homology capture high-order structural information so as to augment graph neural network methods. However, computing extended persistent ho…