On Functional Test Generation for Deep Neural Network IPs

no code implementations • 23 Nov 2019 • Bo Luo, Yu Li, Lingxiao Wei, Qiang Xu

Considering the large amount of training data and know-how required to generate the network, it is more practical to use third-party DNN intellectual property (IP) cores for many designs.

I Know What You See: Power Side-Channel Attack on Convolutional Neural Network Accelerators

no code implementations • 5 Mar 2018 • Lingxiao Wei, Bo Luo, Yu Li, Yannan Liu, Qiang Xu

Deep learning has become the de-facto computational paradigm for various kinds of perception problems, including many privacy-sensitive applications such as online medical image analysis.

Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networks

no code implementations • 15 Jan 2018 • Bo Luo, Yannan Liu, Lingxiao Wei, Qiang Xu

Previous adversarial example crafting methods, however, use simple metrics to evaluate the distances between the original examples and the adversarial ones, which could be easily detected by human eyes.