Overview

My research is driven by a passion for developing artificial intelligence systems that are not only powerful but also trustworthy and reliable, ensuring its’ responsible and ethical deployment. Currently, I focus on three key areas:

• Trustworthy Machine Learning: I am exploring methods to enhance the transparency, fairness, and robustness of machine learning models, ensuring they make decisions that are understandable, unbiased, and resilient to adversarial attacks.
• Large Language Models: I am investigating the capabilities and limitations of large language models, with a focus on their potential applications in various domains while addressing concerns related to bias, misinformation, and ethical use.
• AI for Medicine & Healthcare: I am interested in leveraging AI to improve healthcare outcomes, from disease diagnosis and treatment planning to drug discovery and personalized medicine. My goal is to develop AI solutions that are safe, effective, and accessible to all.

RQ1: How we define GenAI system's threat surface?

Rasheed, Khansa, et al. "Explainable, trustworthy, and ethical machine learning for healthcare: A survey." Computers in Biology and Medicine 149 (2022): 106043.​

RQ2: How we do high availability offensive red teaming?

Derczynski, Leon, et al. "garak: A Framework for Security Probing Large Language Models." arXiv preprint arXiv:2406.11036 (2024).

Publications

(* indicate corresponding author)

A Survey on Gait Recognition Against Occlusion: Taxonomy, Dataset and Methodology

Tianhao Li, Weizhi Ma, Yujia Zheng, Xinchao Fan, Guangcan Yang, Lijun Wang, Zhengping Li*

PeerJ Computer Science, 2024 (SCI, JCR-Q1, Undergoing Major Revision)

SFSWTS: EEG Emotion Recognition Based on Spatial-frequency Shifted Windows Time Self-attention Neural Network

Weizhi Ma, Ying Li*, Tianhao Li, Haowei Yang, Zhengping Li, Lijun Wang, Junyu Xuan

Pattern Recognition, 2024 (SCI, JCR-Q1, Undergoing Peer Review)

A comprehensive review of deep learning in EEG-based emotion recognition: classifications, trends, and practical implications

Weizhi Ma, Yujia Zheng, Tianhao Li, Zhengping Li, Ying Li, Lijun Wang*

PeerJ Computer Science, 2024 (SCI, JCR-Q1)

Trustworthy Metaverse: A Comprehensive Investigation into Security Risks and Privacy Issues in Artificial Intelligence‐Extended Reality Systems

Tianhao Li, Yujia Zheng, Weizhi Ma, Guangshuo Wang, Zhengping Li, Lijun Wang*

SID Symposium Digest of Technical Papers, 2024 (EI-Compendex)

Unveiling Privacy Challenges: Big Data‐Driven Digital Twins in Smart City Applications

Yujia Zheng, Tianhao Li, Weizhi Ma, Jiaxiang Zheng, Zhengping Li, Lijun Wang*

SID Symposium Digest of Technical Papers, 2024 (EI-Compendex)

Automated Pricing and Replenishment Decision for Vegetable Products Based on Hybrid Machine Learning Models

Yujia Zheng, Tianhao Li, Weizhi Ma, Zhengping Li, Lijun Wang, Ying Li*

Electronics, Communications and Networks, 2024 (EI-Compendex)

Research on Real-time Early Warning Mechanism of Aviation Safety Based on Finite State Machine Underlying in QAR Stream Data

Tianhao Li, Yujia Zheng, Haoan Zhang, Weizhi Ma, Ying Li*

Proceedings of the 2023 7th International Conference on Big Data and Internet of Things, 2023 (EI-Compendex)

Collaborators

• Lijun Wang, PhD, Professor/Director, Advance Vision Research Institute, Hangzhou Institute of Technology, Xidian University
• Guangcan Yang, PhD, Professor, North China University of Technology
• Junyu Xuan, PhD, Senior Lecturer, University of Technology Sydney