Yanzhi Wang

A Profit Optimization Framework of Energy Storage Devices in Data Centers: Hierarchical Structure and Hybrid Types

2016

This paper investigates the hierarchical deployment and over-provisioning of energy storage devices (ESDs) in data ceners by (i) adopting a realistic power delivery architecture (from Intel) for centralized ESD structure as the starting point, (ii) …

An ADMM-Based Universal Framework for Adversarial Attacks on Deep Neural Networks

2018

Deep neural networks (DNNs) are known vulnerable to adversarial attacks. That is, adversarial examples, obtained by adding delicately crafted distortions onto original legal inputs, can mislead a DNN to classify them as any target labels. …

Evaluating Fault Resiliency of Compressed Deep Neural Networks

2019

Model compression is considered to be an effective way to reduce the implementation cost of deep neural networks (DNNs) while maintaining the inference accuracy. Many recent studies have developed efficient model compression algorithms and implementations …