Jiacen(Jason) Xu

嘉涔 徐

I am a first-year Ph.D. student in DSP Lab, Department of Electrical Engineering and Computer Science at University of California, Irvine. My advisor is Prof. Zhou Li.

I received my B.S. and Master degree from Shanghai Jiao Tong University and got Outstanding Undergraduate in 2017 and Outstanding Graduate in 2020.

Email  /  Github  /  Google Scholar  /  Twitter  /  Blogs

profile photo
  • I pass the Ph.D. Preliminary Examination on November 2020.
  • I become a Ph.D. student at University of California, Irvine on September 2020.

My research interests include Adversarial Machine Learning and Data-driven Security. Much of my research is about inferring the physical world and real world applications. Representative papers are highlighted.

An Empirical and Comparative Analysis of Data Valuation with Scalable Algorithms
Ruoxi Jia, Xuehui Sun, Jiacen Xu, Ce Zhang, Bo Li, Dawn Song
arXiv, 2019
project page / arXiv

In this work, we develop a simple and efficient heuristic for data valuation based on the Shapley value with complexity independent with the model size.

Towards a unified min-max framework for adversarial exploration and robustness
Jingkang Wang, Tianyun Zhang, Sijia Liu, Pin-Yu Chen, Jiacen Xu, Makan Fardad, Bo Li
arXiv, 2019

By solving a min-max problem, the self-adjusted domain weights learned from our method provides a means to explain the difficulty level of attack and defense over multiple domains.

Great thanks to Jon Barron and Yingwei Li.