I am currently a Ph.D. candidate at Tsinghua University under the supervision of Professor Chao Zhang and Zongpeng Li. I received a B.E. from Huazhong University of Science and Technology (HUST) in 2019 (with the highest honor). My primary research interests lie in artificial intelligence (AI) security. Specifically, I focus on the following areas:
- AI security in the computer vision domain, such as adversarial, backdoor, and bit-flip attacks.
- AI security in other domains (such as learning-based malware detectors, and binary similarity detection models).
- AI interpretability.
Email: wang-jl22@mails.tsinghua.edu.cn or wangjialai97@gmail.com
Publications
Conferences
Aegis: Mitigating Targeted Bit-flip Attacks against Deep Neural Networks
Jialai Wang, Ziyuan Zhang, Meiqi Wang, Han Qiu, Tianwei Zhang, Qi Li, Zongpeng Li, Tao Wei, Chao Zhang
To appear in the 32nd USENIX Security Symposium (USENIX Security’23), Anaheim, CA, USA, AUGUST 9–11 2023
MPass: Bypassing Learning-based Static Malware Detectors
Jialai Wang, Wenjie Qu, Yi Rong, Han Qiu, Qi Li, Zongpeng Li, Chao Zhang
To appear in the Design Automation Conference (DAC’23), San Francisco, CA, USA, July 9-13 2023
BET: Black-box Efficient Testing for Convolutional Neural Networks
Jialai Wang, Han Qiu, Yi Rong, Hengkai Ye, Qi Li, Zongpeng Li, Chao Zhang
To appear in the ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA’22), Daejeon, South Korea, July 2022
Journals
A Survey of Intelligent Malware Detection on Windows Platform
Jialai Wang, Chao Zhang, Xuyan Qi, Yi Rong
Journal of Computer Research and Development, 2021, 58(5): 977-994