Xi Li

Assistant Professor, Computer Science, University of Alabama at Birmingham

Joined

September 2022

Names

Xi Li (Preferred)

Emails

****@psu.edu (Confirmed)

****@uab.edu (Confirmed)

Personal Links

Homepage

Google Scholar

Career & Education History

Assistant Professor

Computer Science , University of Alabama at Birmingham (uab.edu)

2024 – Present

PhD student

Computer Science and Engineering, Pennsylvania State University (psu.edu)

2018 – 2024

Advisors, Relations & Conflicts

PhD Advisor

George Kesidis

2019 – 2024

PhD Advisor

David Miller

2019 – 2024

Expertise

Machine Learning

Present

Adversarial Machine Learning

Present

Deep Learning

Present

Publications

Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards
Xi Li, Shu Zhao, Xiaohan Zou, Fei Zhao, Fuxiao Liu, Yusen Zhang, Cheng Han, Yushun Dong, Jiaqi Wang
- ICLR 2026 Trustworthy AI
- Readers: Everyone
Benchmarking LLM-Assisted Blue Teaming via Standardized Threat Hunting
Yuqiao Meng, Xiaoqun Liu, Luoxi Tang, Feiyang Yu, Xi Li, Guanhua Yan, Ping Yang, Zhaohan Xi
- ICLR 2026 Conference Desk Rejected Submission
- Readers: Everyone
AAAR-1.0: Assessing AI’s Potential to Assist Research
Renze Lou, Hanzi Xu, Sijia Wang, Jiangshu Du, Ryo Kamoi, Xiaoxin Lu, Jian Xie, Yuxuan Sun, Yusen Zhang, Jihyun Janice Ahn, Hongchao Fang, Zhuoyang Zou, Wenchao Ma, Xi Li, Kai Zhang, Congying Xia, Lifu Huang, Wenpeng Yin
- ICML 2025 poster
- Readers: Everyone
AAAR-1.0: Assessing AI's Potential to Assist Research
Renze Lou, Hanzi Xu, Sijia Wang, Jiangshu Du, Ryo Kamoi, Xiaoxin Lu, Jian Xie, Yuxuan Sun, Yusen Zhang, Jihyun Janice Ahn, Hongchao Fang, Zhuoyang Zou, Wenchao Ma, Xi Li, Kai Zhang, Congying Xia, Lifu Huang, Wenpeng Yin
- AI4Research @ AAAI 2025 Oral
- Readers: Everyone
Unveiling Backdoor Risks Brought by Foundation Models in Heterogeneous Federated Learning
Xi Li, Chen Wu, Jiaqi Wang
- OpenReview Archive Direct Upload
- Readers: Everyone
Temporal-Distributed Backdoor Attack Against Video Based Action Recognition
Xi Li, Songhe Wang, Ruiquan Huang, Mahanth Gowda, George Kesidis
- AAAI-24
- Readers: Everyone
Vulnerabilities of Foundation Model Integrated Federated Learning Under Adversarial Threats
Xi Li, Chen Wu, Jiaqi Wang
- OpenReview Archive Direct Upload
- Readers: Everyone
Backdoor Threats from Compromised Foundation Models to Federated Learning
Xi Li, Songhe Wang, Chen Wu, Hao Zhou, Jiaqi Wang
- FL@FM-NeurIPS’23 Poster
- Readers: Everyone
Backdoor Mitigation by Correcting Activation Distribution Alteration
Xi Li, Zhen Xiang, David Miller, George Kesidis
- 17 Jan 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
Backdoor Mitigation by Correcting Activation Distribution Alteration
Xi Li, Zhen Xiang, George Kesidis, Bo Li, David J. Miller
- Published: 01 Feb 2023, Last Modified: 13 Feb 2023
- Submitted to ICLR 2023
- Readers: Everyone

View all 16 publications

Co-Authors

View all 43 co-authors