Ruihan Wu (吴睿涵)

I am currently a postdoctoral researcher at the University of California, San Diego, fortunately advised by Kamalika Chaudhuri. My research interests mainly lie in trustworthy machine learning, with a focus on privacy and robustness. My recent interests are privacy-preserving machine learning and online adaptation to distribution shift. 

I received my Ph.D. from Cornell University, where I was very fortunate to be advised by Kilian Q. Weinberger. Prior to that, I received my B.E. in computer science from Yao Class at Tsinghua University. 

Email: ruw076 [at] ucsd [dot] edu or rw565 [at] cornell [dot] edu

[Google Scholar][LinkedIn][Github]


Large-Scale Public Data Improves Differentially Private Image Generation Quality

Ruihan Wu, Chuan Guo, Kamalika Chaudhuri

--arXiv 2301.02560. [pdf]

Publications and Manuscripts

Learning To Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learning

Ruihan Wu*, Xiangyu Chen*, Chuan Guo, Kilian Q Weinberger

--In Conference on Uncertainty in Artificial Intelligence (UAI), 2023. [pdf] [code]

Does Label Differential Privacy Prevent Label Inference Attacks?

Ruihan Wu*, Jin Peng Zhou*, Kilian Q Weinberger, Chuan Guo

--In International Conference on Artificial Intelligence and Statistics (AISTATS), 2023. [pdf] [code]

Differentially Private Multi-Party Data Release for Linear Regression

Ruihan Wu, Xin Yang, Yuanshun Yao, Jiankai Sun, Tianyi Liu, Kilian Q Weinberger, Chong Wang

--In Conference on Uncertainty in Artificial Intelligence (UAI), 2022. [pdf] [code][video]

Online Adaptation to Label Distribution Shift

Ruihan Wu, Chuan Guo, Yi Su, Kilian Q. Weinberger

--In Advances of Neural Information Processing (NeurIPS), 2021. [pdf] [code][video]

Fixes That Fail: Self-Defeating Improvements in Machine-Learning Systems

Ruihan Wu, Chuan Guo, Awni Hannun, Laurens van der Maaten

--In Advances of Neural Information Processing (NeurIPS), 2021. [pdf] [code]

Correlator Convolutional Neural Networks as an Interpretable Architecture for Image-like Quantum Matter Data

Cole Miles, Annabelle Bohrdt, Ruihan Wu, Christie Chiu, Muqing Xu, Geoffrey Ji, Markus Greiner, Kilian Q. Weinberger, Eugene Demler, Eun-Ah Kim

--Nature Communications, 2021. [pdf]

Making Paper Reviewing Robust to Bid Manipulation Attacks

Ruihan Wu*, Chuan Guo*, Felix Wu, Rahul Kidambi, Laurens van der Maaten, Kilian Q. Weinberger

--In International Conference on Machine Learning (ICML), 2021. [pdf] [code][video]

On Hiding Neural Networks Inside Neural Networks

Chuan Guo*, Ruihan Wu*, Kilian Q. Weinberger

unpublished manuscript, 2020 [pdf] [code]

Scalable Lattice Influence Maximization

Wei Chen*, Ruihan Wu*, Zheng Yu*

--IEEE Transactions on Computational Social Systems (TCSS), 2020. [pdf]

Product Kernel Interpolation for Scalable Gaussian Processes

Jake Gardner, Geoff Peiss, Ruihan Wu, Kilian Q. Weinberger, Andrew G. Wilson

--In International Conference on Artificial Intelligence and Statistics (AISTATS), 2018.  [pdf]

Quadratic Upper Bound for Recursive Teaching Dimension of Finite VC Classes

 Lunjia Hu, Ruihan Wu, Tianhong Li, Liwei Wang

--In Conference on Learning Theory (COLT), 2017.  [pdf]


Google Differential Privacy for ML Seminar, September 2022. [link]

TrustML Young Scientist Seminar, October 2022. [link]

Selected Awards 

LinkedIn PhD Award, 2022

National Scholarship (top 2% in Tsinghua University), 2017

Gold Medal in Chinese Mathematical Olympiad , 2013