Diversity Helps Jailbreak Large Language Models
Weiliang Zhao, Daniel Ben-Levi, Wei Hao,Junfeng Yang, Chengzhi Mao. "Diversity Helps Jailbreak Large Language Models", arXiv preprint arXiv:2411.04223 (2024).
CV
Education
- Ph.D in ML Systems, Columbia University, 2025 (expected)
- B.S. in Computer Science and Mathematics, UW-Madison, 2019
Work experience
- Summer 2024: Research Internship at Barracuda Networks
- Summer 2023: Research Internship at MSR, System Group
- Summer 2022: Research Internship at MSR, System Group
- Summer 2020: Research Internship at Max Planck Institute for Software Systems
- Summer 2018: Research Internship at Citrine Informatics
Skills
- C++/Python/Cuda/Linux
Publications
I Can Hear You: Selective Robust Training for Deepfake Audio Detection
Zhang, Zirui, Wei Hao, Aroon Sankoh, William Lin, Emanuel Mendiola-Ortiz, Junfeng Yang, and Chengzhi Mao. "I Can Hear You: Selective Robust Training for Deepfake Audio Detection", arXiv preprint arXiv:2411.00121 (2024).
Nazar: Monitoring and Adapting ML Models on Mobile Devices
Wei Hao, Zixi Wang, Lauren Hong, Lingxiao Li, Nader Karayanni, AnMei Dasbach-Prisk, Chengzhi Mao, Junfeng Yang, Asaf Cidon, "Nazar: Monitoring and Adapting ML Models on Mobile Devices", The 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2025.
Learning to Rewrite: Generalized LLM-Generated Text Detection
Wei Hao, Ran Li, Weiliang Zhao, Junfeng Yang, and Chengzhi Mao. "Learning to Rewrite: Generalized LLM-Generated Text Detection", arXiv preprint arXiv:2408.04237 (2024).
MGit: A Model Versioning and Management System
Wei Hao*, Daniel Mendoza*, Rafael Mendes, Deepak Narayanan, Amar Phanishayee, Asaf Cidon, Junfeng Yang, "MGit: A Model Versioning and Management System", The Forty-first International Conference on Machine Learning (ICML), 2024.
A Tale of Two Models: Constructing Evasive Attacks on Edge Models
Wei Hao, Aahil Awatramani, Jiayang Hu, Chengzhi Mao, Pin-Chun Chen, Eyal Cidon, Asaf Cidon, Junfeng Yang, "A Tale of Two Models: Constructing Evasive Attacks on Edge Models", Fifth Conference on Machine Learning and Systems (MLSys), 2022.
Serving DNNs like Clockwork: Performance Predictability from the Bottom Up
Arpan Gujarati, Reza Karimi, Safya Alzayat, Wei Hao, Antoine Kaufmann, Ymir Vigfusson, Jonathan Mace, "Serving DNNs like Clockwork: Performance Predictability from the Bottom Up", 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI), 2020.
Learning Amyloid Pathology Progression from Longitudinal PiB-PET Images in Preclinical Alzheimer’s Disease
Wei Hao, Nicholas M. Vogt, Zihang Meng, Seong Jae Hwang, Rebecca L. Koscik, Sterling C. Johnson, Barbara B. Bendlin, and Vikas Singh, "Learning Amyloid Pathology Progression from Longitudinal PiB-PET Images in Preclinical Alzheimer’s Disease", International Symposium on Biomedical Imaging (ISBI), 2020.
Sparse Convolutions for Faster Object Recognition
Wei Hao and Shivaram Venkataraman, "Sparse Convolutions for Faster Object Recognition", AI Systems Workshop at Symposium on Operating Systems Principles(SOSP), 2019.
Talks
Oral Presentation at OSDI 2020
Talk at 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI '20), Cyber Desert, Online
Oral Presentation at ISBI 2020
Talk at IEEE International Symposium on Biomedical Imaging, Iowa city, Iowa