I am currently a fourth-year Ph.D. student in the Department of Computer Science and Engineering at Washington University in St. Louis, advised by Prof. Ning Zhang. Prior to that, I received dual Bachelor’s degrees in Communication Engineering from University of Electronic Science and Technology of China (UESTC) and University of Glasgow (UoG) (Graduated with First-class honor degree) in 2020. Additionally, I worked as a machine learning engineer at Tencent from 2020 to 2021, and I was an applied scientist intern at Amazon in the summer of 2023. Most recently, I worked as a research scientist intern at Meta in the summer of 2024 and am currently continuing with Meta as a part-time student researcher for the Fall of 2024.

I am expected to graduate in May 2025 and am actively seeking full-time opportunities for research or applied scientist positions. Feel free to contact me at h.liu1@wustl.edu.

Research Interests

• Security and Privacy of Machine Learning, Large Language Model, Generative AI, and Information Retrieval

What’s New

• [September 2024] I will start a new position as Student Researcher in Meta this fall!
• [May 2024] I will start a new position as Research Scientist Intern in Meta this summer!
• [Oct 2023] One paper titled “Please Tell Me More: Privacy Impact of Explainability through the Lens of Membership Inference Attack” got accepted in IEEE S&P 2024!
• [May 2023] I will start a new position as Applied Scientist Intern in Amazon this summer!
• [February 2023] Two papers titled “RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation with Natural Prompts” and “SlowLiDAR: Increasing the Latency of LiDAR-Based Detection Using Adversarial Examples” got accepted in CVPR 2023!
• [February 2023] One paper titled “IP Protection in TinyML” got accepted in DAC 2023!
• [August 2022] One paper titled “When Evil Calls: Targeted Adversarial Voice over IP Network” got accepted in CCS 2022!
• [August 2022] One paper titled “PolyRhythm: Adaptive Tuning of a Multi-Channel Attack Template for Timing Interference” got accepted in RTSS 2022!
• [August 2022] One paper titled “From Timing Variations to Performance Degradation: Understanding and Mitigating the Impact of Software Execution Timing in SLAM” got accepted in IROS 2022!

Publications

Sequential LLM Framework for Fashion Recommendation

Han Liu, Xianfeng Tang, Tianlang Chen, Jiapeng Liu, Indu Indu, Henry Peng Zou, Peng Dai, Roberto Fernandez Galan, Michael D Porter, Dongmei Jia, Ning Zhang, Lian Xiong.
In 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP).
[PDF]

SoK: Security and Privacy Risks of Medical AI

Yuanhaur Chang*, Han Liu*, Evin Jaff, Chenyang Lu, Ning Zhang (* Equal Contribution).
arXiv preprint arXiv:2409.07415.
[PDF]

Please Tell Me More: Privacy Impact of Explainability through the Lens of Membership Inference Attack

Han Liu, Yuhao Wu, Zhiyuan Yu, Ning Zhang.
In IEEE Symposium on Security and Privacy (IEEE S&P), 2024. (Acceptance Rate: 83/558=14.9%)
[PDF]

EIVEN: Efficient Implicit Attribute Value Extraction using Multimodal LLM

Henry Peng Zou, Gavin Heqing Yu, Ziwei Fan, Dan Bu, Han Liu, Peng Dai, Jia Dongmei, Cornelia Caragea.
In 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2024.
[PDF]

RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation with Natural Prompts

Han Liu, Yuhao Wu, Shixuan Zhai, Bo Yuan, Ning Zhang.
In IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023.
[PDF] [Code]

SlowLiDAR: Increasing the Latency of LiDAR-Based Detection Using Adversarial Examples

Han Liu, Yuhao Wu, Zhiyuan Yu, Yevgeniy Vorobeychik, Ning Zhang.
In IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023.
[PDF] [Code]

IP Protection in TinyML

Jinwen Wang*, Yuhao Wu*, Han Liu, Bo Yuan, Roger Chamberlain, Ning Zhang (* Equal Contribution).
In ACM/IEEE Design Automation Conference (DAC), 2023.

When Evil Calls: Targeted Adversarial Voice over IP Network

Han Liu, Zhiyuan Yu, Mingming Zha, XiaoFeng Wang, William Yeoh, Yevgeniy Vorobeychik, Ning Zhang.
In ACM Conference on Computer and Communications Security (CCS), 2022.
[PDF] [Code]

PolyRhythm: Adaptive Tuning of a Multi-Channel Attack Template for Timing Interference

Ao Li*, Marion Sudvarg*, Han Liu, Zhiyuan Yu, Chris Gill, Ning Zhang (* Equal Contribution).
In IEEE Real-Time Systems Symposium (RTSS), 2022.
[PDF] [Code]

From Timing Variations to Performance Degradation: Understanding and Mitigating the Impact of Software Execution Timing in SLAM

Ao Li, Han Liu, Jinwen Wang, Ning Zhang.
In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022.
[PDF] [Code]

Services

Conference Reviewer

• International Conference on Learning Representations (ICLR) 2025
• International Conference on Artificial Intelligence and Statistics (AISTATS) 2025
• Conference on Neural Information Processing Systems (NeurIPS) 2024
• IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2024
• AAAI Conference on Artificial Intelligence (AAAI) 2024, 2025
• International World Wide Web Conference (WWW) 2024
• Annual Meeting of the Association for Computational Linguistics (ACL) 2024
• British Machine Vision Conference (BMVC) 2023

Journal Reviewer

• IEEE Transactions on Information Forensics and Security
• IEEE/ACM Transactions on Networking
• IEEE Transactions on Circuits and Systems for Video Technology
• Journal of Data-centric Machine Learning Research
• Neurocomputing