About me
I am a final-year Ph.D. candidate in the Department of Computer Science at the University of Maryland, College Park (UMD). As a research assistant at UMD, I work with Dr. Tom Goldstein on research topics relevant to AI/ML safety.
My research interest is to develop trustworthy machine learning (AI/ML) systems, for which I have worked on model reliability, interpretability, and AI/ML safety. I have broad interests and experience in studying these problems for different ML systems, including vision-language models, large language models (LLMs), and image generative diffusion models.
During Ph.D., I have interned at Nvidia, Salesforce and Google as a research intern, where I have collaborated with many awesome professors and researchers.
Before UMD, I obtained my bachelor’s degree in information security at the University of Science and Technology of China (USTC) in June 2019.
News
- [09/2023] One paper accepted at NeurIPS. We studied a novel vulnerability of aligned language models from the perspective of data security.
- [11/2022] In New Orleans attending NeurIPS. Will present the work done at Nvidia about prompt tuning for vision-language models. (Excited to attend my first in-person academic conference. I wish I had printed a bigger poster.)
Selected Publications
For the complete list of publications, please refer to my google scholar page
On the Exploitability of Instruction Tuning
M. Shu, J. Wang, C. Zhu, J. Geiping, C. Xiao, T. Goldstein
to appear at NeurIPS 2023
[Preprint] [Code]On the Reliability of Watermarks for Large Language Models
J. Kirchenbauer*, J. Geiping*, Y. Wen, M. Shu, K. Saifullah, K. Kong, K. Fernando, A. Saha, M. Goldblum, T. Goldstein
Under review
[Preprint] [Code]Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models
M. Shu, W. Nie, D.A. Huang, Z. Yu, T. Goldstein, A. Anandkumar, C. Xiao
NeurIPS 2022
[Paper] [Code] [Project page]Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability
R. Levin*, M. Shu*, E. Borgnia*, F. Huang, M. Goldblum, T. Goldstein
NeurIPS 2022
[Paper] [Code]The Close Relationship Between Contrastive Learning and Meta-Learning
R. Ni*, M. Shu*, H. Souri, M. Goldblum, T. Goldstein
ICLR 2022
[Paper] [Code]Encoding Robustness to Image Style via Adversarial Feature Perturbation
M. Shu, Z. Wu, M. Goldblum, T. Goldstein
NeurIPS 2021
[Paper] [Code]Adversarial Differentiable Data Augmentation for Autonomous Systems
M. Shu, Y. Shen, M.C. Lin, T. Goldstein
ICRA 2021
[Paper] [Code]Model-Agnostic Hierarchical Attention for 3D Object Detection
M. Shu, L. Xue, R. Mart'in-Mart'in, C. Xiong, T. Goldstein, J.C. Niebles, R. Xu.
Under review
[Preprint]
Services
Conference reviewer: NeurIPS, ICML, ICLR, CVPR, ICCV, IROS
Journal reviewer: IJCV
More about me (misc)
I enjoy doing yoga and meditation. I listen to classical music when focusing. I haven’t played many video games, but I had great times playing The Legend of Zelda (BotW) and Stardew Valley.