Biography

Tianhao Li is a thesis-track MSc candidate in Medical Physics at Duke University (DKU-based), where he work with Prof. Fang-Fang Yin and Prof. Zhenyu Yang. He also serves as a visiting researcher at the University of Wisconsin-Madison, under supervision of Prof. Chaowei Xiao. His primary research focus lies in Safety & Privacy for Healthcare Foundation Model. Tianhao received a BEng in Information Security in 2024 and leads the Special Interest Group in Modern Interdisciplinary Research (SIGMIR). He also serves as peer reviewers for prestigious journals, conferences, and workshops, including TIST, TAI, TBE, EAAI, RESS, JBHI, AAAI, IJCAI, ICLR, and ACL, etc.. In addition, Tianhao contribute to the MLCommons AI Risk & Reliability (AIRR) Working Group, and the NVIDIA’s widely recognized open-source project NVIDIA/garak (4.2K+ stars on Github).

[Email: tianhao.li2@duke.edu] | [Meeting Schedule] | [PGP Public Key]

[Curriculum Vitae] | [Research Statement] | [Teaching Statement] | [Diversity Statement]

Open to collaboration: Special Interest Group in Modern Interdisciplinary Research (SIGMIR) is a voluntary-based virtual research group, open to all students, researchers, and faculty members. If you are interested in joining, please fill in the Google Form.

News

[Apr 2025] Our paper SFSWTS: A Spatial-Frequency Shifted Windows and Time Self-Attention Network for EEG Emotion Recognition has been accepted by Neurocomputing (JCR-Q1), congrats Weizhi!
[Mar 2025] Our paper Synthetic Poisoning Attacks: The Impact of Poisoned MRI Image on U-Net Brain Tumor Segmentation has been accepted by ICLR 2025 SynthData, see you in Singapore EXPO!
[Dec 2024] Our paper SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks has been accepted by AAAI 2025 AICS as oral presentation, see you in Philadelphia, Pennsylvania, USA!
[Dec 2024] Our survey paper A survey on gait recognition against occlusion: taxonomy, dataset and methodology has been published by PeerJ Computer Science (JCR-Q1)!
[Dec 2024] 7 papers from SIGMIR have been accepted by ICDT 2025 as oral presentations, congrats to Jingyu, Tianyu, Chuangxin, and Haotian!
[May 2024] Our survey paper A comprehensive review of deep learning in EEG-based emotion recognition: classifications, trends, and practical implications has been published by PeerJ Computer Science (JCR-Q1)!
[Nov 2023] Tianhao will give 2 oral presentations and 1 poster presentation at MLIS'24 for 3 accepted papers from SIGMIR, see you in Macau!
[Aug 2023] Tianhao will give an oral presentation at BDIoT'23 about the accepted paper Research on Real-time Early Warning Mechanism of Aviation Safety Based on Finite State Machine Underlying in QAR Stream Data.