19 citations · 19 across the 2 of their papers we have counts for
3 papers
cs.CR2022★ 19 cited
Rethinking the Reverse-engineering of Trojan Triggers
Zhenting Wang, Kai Mei, Hailun Ding +2
Deep Neural Networks are vulnerable to Trojan (or backdoor) attacks. Reverse-engineering methods can reconstruct the trigger and thus identify affected models. Existing reverse-eng…
cs.LG2019
Understanding the Importance of Single Directions via Representative Substitution
Li Chen, Hailun Ding, Qi Li +3
Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior. The interpretation of individual units, which are neurons in MLPs or…
cs.CV2018
Understanding the Importance of Single Directions via Representative Substitution
Li Chen, Hailun Ding, Qi Li +3
Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior. The interpretation of individual units, which are neurons in MLPs or…