19 citations · 31 across the 5 of their papers we have counts for
5 papers
DUPIN: Attack Learning Is Still Needed! Demonstrating Few-Shot after Unsupervised Pretraining Is A Nimble Forensics Learner
Chanwoo Bae, Hailun Ding, Shiqing Ma +1
We propose a novel approach to learning-based attack forensics called DUPIN. DUPIN performs unsupervised pre-training on an enormous amount of audit events in the form of provenanc…
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…
Training with More Confidence: Mitigating Injected and Natural Backdoors During Training
Zhenting Wang, Hailun Ding, Juan Zhai +1
The backdoor or Trojan attack is a severe threat to deep neural networks (DNNs). Researchers find that DNNs trained on benign data and settings can also learn backdoor behaviors, w…
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…
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…