Bio
I'm a researcher at ByteDance Research in Mountain View, CA. I do research in trustworthy (responsible) AI, i.e. machine learning security, privacy, fairness, and interpretability with a recent focus on large language model.
I got Ph.D. in Computer Science from University of Chicago, advised by Prof. Ben Zhao and Prof. Heather Zheng. Previously I got three B.S. degrees in Computer Science, Mathematics, and Statistics from University of Minnesota-Twin Cities.
I interned at Google and received Siebel Scholarship. My work is covered by a number of mainstream media outlets, e.g. WIRED, Business Insider, Scientific American, Forbes, Fortune, The Verge, Engadget, New York Post, and Nvidia etc.
I sometimes write for my own pleasure.
Publications
- Large Language Model Unlearning
Workshop of Socially Responsible Language Modelling Research (SoLaR) at NeurIPS 2023.
Yuanshun Yao, Xiaojun Xu, Yang Liu
- Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models' Alignment
Workshop of Socially Responsible Language Modelling Research (SoLaR) at NeurIPS 2023.
Yang Liu*, Yuanshun Yao*, Jean-Francois Ton, Xiaoying Zhang, Ruocheng Guo, Hao Cheng, Yegor Klochkov, Muhammad Faaiz Taufiq, Hang Li.
- Understanding Unfairness via Training Concept Influence
Proceedings of Data-centric Machine Learning Research (DMLR) Workshop at ICML 2023.
Yuanshun Yao, Yang Liu
- Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributes
Proceedings of International Conference on Machine Learning (ICML), July 2023.
Zhaowei Zhu*, Yuanshun Yao*, Jiankai Sun, Hang Li, Yang Liu
- "My face, my rules": Enabling Personalized Protection against Unacceptable Face Editing
Proceedings of Privacy Enhancing Technologies Symposium (PETS), July 2023.
Zhujun Xiao, Jenna Cryan, Yuanshun Yao, Yi Hong Gordon Cheo, Yuanchao Shu, Stefan Saroiu, Ben Y. Zhao, Haitao Zheng.
- DPAUC: Differentially Private AUC Computation in Federated Learning
Proceedings of AAAI Conference on Artificial Intelligence (AAAI), February 2023.
Jiankai Sun, Xin Yang, Yuanshun Yao, Junyuan Xie, Di Wu, Chong Wang
- Netflix and Forget: Fast Severance From Memorizing Training Data in Recommendations
Proceedings of NeurIPS ML Safety Workshop, November 2022.
Mimee Xu, Jiankai Sun, Xin Yang, Yuanshun Yao, Chong Wang
- Differentially Private Multi-Party Data Release for Linear Regression
Proceedings of Conference on Uncertainty in Artificial Intelligence (UAI), August 2022
Ruihan Wu, Xin Yang, Yuanshun Yao, Jiankai Sun, Tianyi Liu, Kilian Q Weinberger, Chong Wang
- Defending against Reconstruction Attack in Vertical Federated Learning
Proceedings of International Workshop on Federated Learning for User Privacy and Data
Confidentiality (Conjunction with ICML), 2021
Jiankai Sun, Yuanshun Yao, Weihao Gao, Junyuan Xie, Chong Wang
- Backdoor Attacks Against Deep Learning Systems in the Physical World
Proceedings of IEEE Computer Vision and Pattern Recognition (CVPR). June 2021
Emily Wenger, Josephine Passananti, Arjun Nitin Bhagoji, Yuanshun Yao, Haitao Zheng, Ben Y. Zhao
- Practical Backdoor Attacks and Defenses in Deep Learning Systems
PhD Thesis, University of Chicago. August 2020
Yuanshun Yao
- Latent Backdoor Attacks on Deep Neural Networks
Proceedings of ACM Conference on Computer and Communications Security (CCS). London, UK,
November 2019
Yuanshun Yao, Huiying Li, Haitao Zheng, Ben Y. Zhao
- Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
Proceedings of 40th IEEE Symposium on Security and Privacy (IEEE S&P). San Francisco, CA, May 2019
Bolun Wang, Yuanshun Yao, Shawn Shan, Huiying Li, Bimal Viswanath, Haitao Zheng, Ben Y. Zhao
- With Great Training Comes Great Vulnerability: Practical Attacks against Transfer Learning
Proceedings of 27th USENIX Security Symposium (USENIX Security). Baltimore, MD, August 2018
Bolun Wang, Yuanshun Yao, Bimal Viswanath, Haitao Zheng, Ben Y. Zhao
- Complexity vs. Performance: Empirical Analysis of Machine Learning as a Service
Proceedings of 17th ACM SIGCOMM Internet Measurement Conference (IMC). London, UK, November 2017
Yuanshun Yao, Zhujun Xiao, Bolun Wang, Bimal Viswanath, Haitao Zheng, Ben Y. Zhao
- Automated Crowdturfing Attacks and Defenses in Online Review Systems
Proceedings of ACM Conference on Computer and Communications Security (CCS). Dallas, TX, October 2017
Yuanshun Yao, Bimal Viswanath, Jenna Cryan, Haitao Zheng, Ben Y. Zhao
- Object Recognition and Navigation using a Single Networking Device
Proceedings of 15th ACM International Conference on Mobile Systems, Applications, and Services (MobiSys).
Niagara Falls, NY, June 2017
Yanzi Zhu, Yuanshun Yao, Ben Y. Zhao, Haitao Zheng
- Identifying Value in Crowdsourced Wireless Signal Measurements
Proceedings of 26th World Wide Web Conference (WWW). Perth, Australia, April 2017
Zhijing Li, Ana Nika, Xinyi Zhang, Yanzi Zhu, Yuanshun Yao, Ben Y. Zhao, Haitao Zheng
- A General Framework to Increase the Robustness of Model-based Change Point Detection Algorithms to Outliers and Noise
Proceedings of SIAM International Conference on Data Mining (SDM). Miami, FL, May 2016
Xi C. Chen, Yuanshun Yao, Sichao Shi, Snigdhansu Chatterjee, Vipin Kumar, James H. Faghmous
- A Daily Global Mesoscale Ocean Eddy Dataset from Satellite Altimetry
Scientific Data 2, Nature Publishing Group. June 2015
James H. Faghmous, Ivy Frenger, Yuanshun Yao, Robert Warmka, Aron Lindell, Vipin Kumar
Leisure Writing
