Liuwan Zhu
Assistant Professor
University of Hawaii at Manoa
Biography
I am an assistant professor in Electrical & Computer Engineering at the University of Hawaiʻi at Mānoa. I received my Ph.D. in Electrical & Computer Engineering from Old Dominion University, US, in 2023, advised by Dr. Hongyi Wu and Dr. Chunsheng Xin, and B.S. degree in Computer Science from Hunan University, China, in 2017. My research interests in the intersection of cybersecurity and AI. On the one hand, investigate using machine learning/deep learning to solve security problem in computer system or cyber-physical system; on the other hand, investigate the robustness and safety of the AI systems(such as Computer Vision, Vision-Language Multi-Modal models), including adversarial attack and backdoor attack.
Download my resumé .
- Machine Learning/Deep Learning for Cybersecurity
- Robustness and Security of AI model
- Vision-Language Multi-Modal Learning
PhD in Electrical and Computer Engineering, 2017 - 2023
Old Dominion University
BSc in Computer Science, 2013 - 2017
Hunan University
Recent Publications
L. Zhu, R. Ning, J. Li, C. Xin, and H. Wu, “SEER: Backdoor Detection for Vision-Language Models through Searching Target Text and Image Trigger Jointly. AAAI Conference on Artificial Intelligence. 2024.
L. Zhu, R. Ning, J. Li, C. Xin, and H. Wu, “Most and Least Retrievable Images in Visual-Language Query Systems”, in Proceedings of the European Conference on Computer Vision (ECCV), Tel Aviv, October 23-27, 2022. [PDF]
L. Zhu, R. Ning, C. Xin, and H. Wu, “CLEAR: Clean-up Trigger-Free Backdoor in Neural Networks”, in Proceedings of the IEEE International Conference on Computer Vision (ICCV), October 11-17, 2021. [PDF]
L. Zhu, R. Ning, C. Wang, C. Xin, and H. Wu, “GangSweep: Sweep out Neural Backdoors by GAN”, in ACM International Conference on Multimedia (MM), Seattle, WA, October 12-16 , 2020. [PDF]
R. Ning, C. Wang, C. Xin, J. Li, L. Zhu, and H. Wu, “CapJack: Capture In-Browser Crypto-jacking by Deep Capsule Network through Behavioral Analysis”, in IEEE International Conference on Computer Communications (INFOCOM), Paris, France, April 29-May 2, 2019. (Best In-session Presentation Award). [PDF]
Grants
- Planning: DCL EPSCOR: SaTC Frontier: Ensuring Security and Privacy in AI-Enabled Cyber-Physical Systems, NSF, $200,000, 2024-2026, Role: Co-PI
- Developing a Holistic Evaluation Framework for Multi-Modal AI Security and Trustworthiness on Smart IoT Devices in NextG Wireless Networks, CCI, $50,000, 2023-2024, Role: Senior Personnel
Mentoring
- Haoyang Xu, PhD, UHM
- Adrian Peng, Master, UHM
- Gavin Ng, Master, UHM
Teaching
EE/ICS660. Computer Architecture [Instructor] (Fall 2023)
GenCyber Summer Camp(Funded by NSA) [Instructor] (Summer 2019-2022)
DeapSECURE Workshop Series(Funded by NSF CyberTraining) [Instructor] (2019-2021)
CYSE635. AI Security and Privacy [Guest Lecturer] (Fall 2021)
CYSE301. Cybersecurity Techniques and Operations [Student Mentor] (Spring 2023)
ECE355. Introduction to Networks and Data Communications [Teatching Assistant] (Fall 2018)
Services
As a Reviewer:
- IEEE Transaction of Mobile Computing(TMC)
- IEEE Transactions on Information Forensics & Security(T-IFS)
- Pervasive and Mobile Computing Journal (PMC)
- IEEE/CVF CVPR 2023
- ACM MultiMedia 2023/2024
TPC member:
- IEEE ICNC 2024
- ACM WiSec 2024
Faculty Mentor:
- UHM Vertically Integrated Projects (VIP)
- NSF REU sites at School of Cybersecurity, 2023