Zhe Zhao
Scholar

Zhe Zhao

Google Scholar ID: OIfDICcAAAAJ
Ant Group
Trustworthy AIAdversarial ExamplesLLM Security
Citations & Impact
All-time
Citations
806
 
H-index
13
 
i10-index
14
 
Publications
20
 
Co-authors
5
list available
Publications
20 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • Published multiple papers in top conferences and journals such as USENIX, SAS, TOSEM, ASE, TDSC, ISSTA, CAV, IEEE S&P; Won several awards including 2nd Place Prize in MLSec Face Recognition Challenge, 5th Place in CVPR 2022 AISafety Challenge Track2, Merit Prize in OPPO 2021 Security AI Challenge, China National Scholarship, etc.
Research Experience
  • 2023.07 - Present RealAI, Research Engineer; 2022.07 - 2023.07 Singapore Management University, Research Assistant; 2016.06 - 2018.01 Hewlett Packard Enterprise / DXC technology, Software Engineer
Education
  • 2018.07 - 2023.07 ShanghaiTech University, PhD, Supervisor: Prof. Song Fu; 2012.08 - 2016.06 Ocean University of China, Undergraduate Student
Background
  • Research interests include trustworthy AI, software testing and verification, such as the robustness of large language models (LLMs), adversarial attack and defense, neural network testing, etc.
Miscellany
  • Served as a Teaching Assistant for Software Engineering at ShanghaiTech University; Participated in various academic conference services, such as Committee member for OSDI and Usenix ATC AEC (2022), ISSTA AEC (2022), Reviewer for ISSRE (2022, 2021), ICECCS (2022, 2020, 2019), ICICS (2022, 2021), CAV (2020), AsianHOST (2022)