14 citations · 17 across the 2 of their papers we have counts for
2 papers
cs.CR2018★ 14 cited
DeepObfuscation: Securing the Structure of Convolutional Neural Networks via Knowledge Distillation
Hui Xu, Yuxin Su, Zirui Zhao +3
This paper investigates the piracy problem of deep learning models. Designing and training a well-performing model is generally expensive. However, when releasing them, attackers m…
cs.SE2017★ 3 cited
On Benchmarking the Capability of Symbolic Execution Tools with Logic Bombs
Hui Xu, Zirui Zhao, Yangfan Zhou +1
Symbolic execution now becomes an indispensable technique for software testing and program analysis. There are several symbolic execution tools available off-the-shelf, and we need…