Towards Robust AI: A Test Perspective
ID:6 View Protection:ATTENDEE Updated Time:2021-08-14 15:07:53 Hits:688 Keynote speech

Start Time:2021-08-19 11:15(Asia/Shanghai)

Duration:45min

Session:PS Plenary Session(Openning, Keynotes 1-6) » PS1Openning and Keynote 1/2/3

No files

Abstract
While deep learning systems have outperformed humans in many domains, they may behave poorly when the test cases are not i.i.d. to the training samples, let alone carefully crafted adversarial examples. In this talk, we discuss problems and opportunities towards robust AI from a test perspective, including offline test solutions to ensure sufficient data-driven coverage and online test solutions to reject adversarial examples and out-of-distribution samples.
Keywords
Speaker
Qiang Xu
Associate Professor The Chinese University of Hong Kong

Prof. Qiang Xu, The Chinese University of Hong Kong
Qiang Xu is an Associate Professor of Computer Science & Engineering at The Chinese University of Hong Kong. He received his B.E. and M.E. degrees in Telecommunication Engineering from Beijing University of Posts & Telecommunications, China, in 1997 and 2000, respectively. After working at a start-up integrated circuit design house for one and a half years, he continued his graduate study and received his Ph.D. degree in Electrical & Computer Engineering from McMaster University, Canada, in 2005, and then joined CUHK.
Dr. Xu leads the CUhk REliable computing laboratory (CURE Lab.) and CUHK MakerLab. His research interests include fault-tolerant computing, trusted computing and smart hardware design. He received the Best Paper Award in 2004 IEEE/ACM Design, Automation and Test in Europe (DATE). He has five other papers nominated for best paper award at prestigious conferences (e.g., DAC and ICCAD).
Dr. Xu is currently serving as an associate editor for IEEE Design&Test. He has also served as technical program committee members for a number of conferences on VLSI design and testing, including DAC, ITC, ICCAD, and DATE.

Submit Comment
Verify Code Change Another
All Comments
Important Date
  • Conference Date

    Aug 18

    2021

    to

    Aug 20

    2021

  • May 10 2021

    Draft paper submission deadline

  • Aug 16 2021

    Early Bird Registration

  • Aug 19 2021

    Contribution Submission Deadline

  • Aug 20 2021

    Registration deadline

Sponsored By
IEEE
Tongji University
Chinese Computer Federation
Organized By
Tongji University
Previous Conferences