Hanxi Guo

About Me

I am currently a second-year Ph.D. student in Computer Science at Purdue University, advised by Prof. Xiangyu Zhang. Before joining Purdue, I received both of my M.Eng. degree and B.Eng. degree in Computer Science from Shanghai Jiao Tong University (SJTU), where I was supervised by Prof. Ruhui Ma and Prof. Tao Song. I also worked with Prof. Yang Hua, and Prof. Hao Wang.

My research interests center around AI Security and Ethics, especially for such topics in Federated Learning and Large Language Models.

News

• [Jun. 2025]Our paper “JailbreakDiffBench: A Comprehensive Benchmark for Jailbreaking Diffusion Models.” is accepted by ICCV 2025. Congrats to Xiaolong!
• [Jun. 2025]Our paper “SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks.” is accepted by USENIX Security 2025. Congrats to Kaiyuan!
• [Oct. 2024]Our paper “MultiVerse: Exposing Large Language Model Alignment Problems in Diverse Worlds.” is accepted by NeurIPS 2024 Workshop on Safe GenAI. Congrats to Xiaolong!
• [Oct. 2024]Our paper “SkewAct: Red Teaming Large Language Models via Activation-Skewed Adversarial Prompt Optimization.” is accepted by NeurIPS 2024 Workshop on Red Teaming GenAI.
• [Sept. 2024]Our paper “BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens.” is accepted by NeurIPS 2024.
Show more
[Sept. 2024]Our paper “BAIT: Large Language Model Backdoor Scanning by Inverting Attack Target.” is accepted by S&P 2025. Congrats to Guangyu!
[Jul. 2024]Our new preprint “Poisoning with A Pill: Circumventing Detection in Federated Learning.” has been released, introducing a generic and attack-agnostic augmentation approach to enhance the effectiveness and stealthiness of existing poisoning attacks in federated learning.
[Jul. 2024]Our paper “UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening.” is accepted by ECCV 2024. Congrats to Siyuan!
[Feb. 2024]Our paper “Our paper “Siren⁺: Robust Federated Learning with Proactive Alarming and Differential Privacy.” is accepted by IEEE TDSC.
[Aug. 2021]Our paper “Siren: Byzantine-robust Federated Learning via Proactive Alarming.” is accepted by SoCC 2021.
[Aug. 2021]Our paper “SpaceDML: Enabling Distributed Machine Learning in Space Information Networks.” is accepted by IEEE Network.

Publications

(* represents equal contribution)

Education

Ph.D. in Computer Science

• Purdue University
• Aug. 2023 - Present
• Advised by Prof. Xiangyu Zhang

M.Eng. in Computer Technology

• Shanghai Jiao Tong University
• Sept. 2020 - Mar. 2023
• Advised by Prof. Ruhui Ma and Prof. Tao Song

B.Eng. in Computer Science and Technology (IEEE Honor Class)

• Shanghai Jiao Tong University
• Sept. 2016 - Jun. 2020
• Advised by Prof. Ruhui Ma and Prof. Tao Song

Work Experience

Graduate Technical Intern

• Intel Asia-Pacific Research and Development Ltd.
• Oct. 2020 - Mar. 2023
• Advised by Ningxin Hu

Student Developer

• Google Summer of Code
• May 2021 - Sept. 2021
• Project: Accelerate OpenCV.js DNN via WebNN (merged to OpenCV: link)

Talks

Accelerate OpenCV.js DNN Module via WebNN

• OpenCV Webinar in OpenCV Chinese Channel, Dec. 2021.

Siren: Byzantine-robust Federated Learning via Proactive Alarming

• The 12th ACM Symposium on Cloud Computing, Nov. 2021.
• SJTU Computer Science Global Lunch Series, Oct. 2021.

Awards

NeurIPS 2024 Scholar Award

• Financial assistance grant for selected attendees at NeurIPS 2024.
• Neural Information Processing Foundation, Oct. 2024.

Shanghai Outstanding Graduate

• The highest honor for graduates in Shanghai, PRC.
• Shanghai Municipal Education Commission, Mar. 2023.

National Scholarship for Graduate Students

• Top 0.2% nationwide.
• Ministry of Education of the People's Republic of China, Dec. 2021.

Services

Conference Reviewer

• Conference on Neural Information Processing Systems (NeurIPS) 2024-2025
• International Conference on Machine Learning (ICML) 2025
• International Conference on Artificial Intelligence and Statistics (AISTATS) 2025
• International Conference on Learning Representations (ICLR) 2025
• EAI CollaborateCom 2022

Journal Reviewer

• IEEE Transactions on Parallel and Distributed Systems (TPDS)
• IEEE Transactions on Dependable and Secure Computing (TDSC)

Powered by Jekyll and Minimal Light theme. Copyright © Hanxi Guo 2024-2025. Last update in Jun. 2025.