Xi Li (李溪)

she/her/hers

Assistant Professor, Ph.D.

University of Alabama at Birmingham

About

I am an Assistant Professor in the Department of Computer Science at the University of Alabama at Birmingham (UAB). I received my Ph.D. in Computer Science from Penn State University under the guidance of Dr. George Kesidis and Dr. David Miller. I obtained my M.S. degree in Computer Science from Penn State University in 2018 and my B.S. degree from the School of Information Science and Engineering at Southeast University in Nanjing, China, in 2016.

Research Interests: My research broadly focuses on trustworthy AI. Recently, we have been exploring the following topics:

Check my resume here.

Publications

Most recent publications are on Google Scholar.

Exploitation and Mitigation: Understanding Large-Scale Machine Learning Robustness under Paradigm Shift

Xi Li, Ruixiang Tang, Muchao Ye

SDM Tutorial, 2025

Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models

Xi Li, Yusen Zhang, Renze Lou, Chen Wu, Jiaqi Wang

Under review

Position Paper: Assessing Robustness, Privacy, and Fairness in Federated Learning Integrated with Foundation Models

Xi Li, Jiaqi Wang

Under review

Backdoor Mitigation by Correcting Distribution of Neural Activation

Xi Li, Zhen Xiang, David Miller, George Kesidis

Neurocomputing, 2024

BIC-based Mixture Model Defense against Data Poisoning Attacks on Classifiers: A Comprehensive Study

Xi Li, David Miller, Zhen Xiang, George Kesidis

IEEE Transactions on Knowledge and Data Engineering (TKDE), 2024

Unveiling Backdoor Risks Brought by Foundation Models in Heterogeneous Federated Learning

Xi Li, Chen Wu, Jiaqi Wang

PAKDD, 2024

Temporal-Distributed Backdoor Attack Against Video-Based Action Recognition

Xi Li, Songhe Wang, Ruiquan Huang, Mahanth Gowda, George Kesidis

AAAI, 2024

Backdoor Threats from Compromised Foundation Models to Federated Learning

Xi Li, Songhe Wang, Chen Wu, Hao Zhou, Jiaqi Wang

FL@FM-NeurIPS'23

A BIC-based Mixture Model Defense against Data Poisoning Attacks on Classifiers

Xi Li, David Miller, Zhen Xiang, George Kesidis

MLSP, 2023

Test-Time Detection of Backdoor Triggers of Poisoned Deep Neural Networks

Xi Li, David Miller, Zhen Xiang, George Kesidis

ICASSP, 2022

Detecting Backdoor Attacks Against Point Cloud Classifiers

Zhen Xiang, David Miller, Siheng Chen, Xi Li, George Kesidis

ICASSP, 2022

A Backdoor Attack against 3D Point Cloud Classifiers

Zhen Xiang, David Miller, Siheng Chen, Xi Li, George Kesidis

ICCV, 2021

Exploitation and Mitigation: Understanding Large-Scale Machine Learning Robustness under Paradigm Shift

Xi Li, Ruixiang Tang, Muchao Ye

SDM Tutorial, 2025

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

Under review

Securing Federated Learning Against Novel and Classic Backdoor Threats During Foundation Model Integration

Xiaohuan Bi, Xi Li

Under review

Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models

Xi Li, Yusen Zhang, Renze Lou, Chen Wu, Jiaqi Wang

Under review

Position Paper: Assessing Robustness, Privacy, and Fairness in Federated Learning Integrated with Foundation Models

Xi Li, Jiaqi Wang

Under review

CEPA: Consensus Embedded Perturbation for Agnostic Detection and Inversion of Backdoors

Guangmingmei Yang, Xi Li, Hang Wang, David Miller, George Kesidis

Under review

Vulnerabilities of Foundation Model Integrated Federated Learning Systems Under Adversarial Threats

Xi Li, Chen Wu, Jiaqi Wang

Under review

Backdoor Mitigation by Correcting Distribution of Neural Activation

Xi Li, Zhen Xiang, David Miller, George Kesidis

Neurocomputing, 2024

BIC-based Mixture Model Defense against Data Poisoning Attacks on Classifiers: A Comprehensive Study

Xi Li, David Miller, Zhen Xiang, George Kesidis

IEEE Transactions on Knowledge and Data Engineering (TKDE), 2024

Unveiling Backdoor Risks Brought by Foundation Models in Heterogeneous Federated Learning

Xi Li, Chen Wu, Jiaqi Wang

PAKDD, 2024

Temporal-Distributed Backdoor Attack Against Video-Based Action Recognition

Xi Li, Songhe Wang, Ruiquan Huang, Mahanth Gowda, George Kesidis

AAAI, 2024

Backdoor Threats from Compromised Foundation Models to Federated Learning

Xi Li, Songhe Wang, Chen Wu, Hao Zhou, Jiaqi Wang

FL@FM-NeurIPS'23

A BIC-based Mixture Model Defense against Data Poisoning Attacks on Classifiers

Xi Li, David Miller, Zhen Xiang, George Kesidis

MLSP, 2023

Test-Time Detection of Backdoor Triggers of Poisoned Deep Neural Networks

Xi Li, David Miller, Zhen Xiang, George Kesidis

ICASSP, 2022

Detecting Backdoor Attacks Against Point Cloud Classifiers

Zhen Xiang, David Miller, Siheng Chen, Xi Li, George Kesidis

ICASSP, 2022

A Backdoor Attack against 3D Point Cloud Classifiers

Zhen Xiang, David Miller, Siheng Chen, Xi Li, George Kesidis

ICCV, 2021

Students

PhD Students

I’m looking for highly motivated PhD students to join my research group starting in Fall 2025 at CS@UAB. Please check the Recruitment page for more details. If you are interested, apply to the CS PhD program and mention my name in your application. Additionally, send your CV and transcript to xili.recruitment@gmail.com with the subject [25Fall PhD Application].

Mentored Students

Teaching

Instructor UAB

Teaching Assistant PSU

Experience

Meta, NYC | Summer 2024

  • Modern Recommendation System Team
  • Machine Learning Engineer Intern
  • Explored early fusion architecture for multimodal understanding.
Meta Logo

Service

Conference Program Committee:

Conference Reviewer:

Journal Reviewer:

Student Volunteer: