2024

1. Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

   Boyi Wei, Kaixuan Huang, Yangsibo Huang, Tinghao Xie, Xiangyu Qi, Mengzhou Xia, Prateek Mittal, Mengdi Wang, and Peter Henderson

   ICLR Secure and Trustworthy LLMs 2024 (Best Paper) Paper Code Website
2. Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment

   Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Yangsibo Huang, Matthew Jagielski, Peter Kairouz, Gautam Kamath, Sewoong Oh, Olga Ohrimenko, Nicolas Papernot, Ryan Rogers, Milan Shen, Shuang Song, Weijie Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Sergey Yekhanin, Da Yu, Huanyu Zhang, and Wanrong Zhang

   Harvard Data Science Review 2024 Paper
3. Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

   Yangsibo Huang, Samyak Gupta, Mengzhou Xia, Kai Li, and Danqi Chen

   ICLR 2024 (spotlight) Paper Code Poster Website Dataset
4. Detecting Pretraining Data from Large Language Modelss

   Weijia Shi, Anirudh Ajith, Mengzhou Xia, Yangsibo Huang, Daogao Liu, Terra Blevins, Danqi Chen, and Luke Zettlemoyer

   ICLR 2024 (Oral at NeurIPS RegML) Paper Code Website Dataset
5. (α) LabelDP-Pro: Learning with Label Differential Privacy via Projections

   Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, and Chiyuan Zhang

   ICLR 2024 Paper

2023

1. (α) Sparsity-Preserving Differentially Private Training

   Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, and Chiyuan Zhang

   NeurIPS 2023 Paper Poster Website
2. Privacy Implications of Retrieval-Based Language Models

   Yangsibo Huang, Samyak Gupta, Zexuan Zhong, Kai Li, and Danqi Chen

   EMNLP 2023 Paper Code
3. kNN-Adapter: Efficient Domain Adaptation for Black-Box Language Models

   Yangsibo Huang, Daogao Liu, Zexuan Zhong, Weijia Shi, and Yin Tat Lee

   Preprint 2023 Paper

2022

1. Recovering Private Text in Federated Learning of Language Models

   Samyak Gupta, Yangsibo Huang, Zexuan Zhong, Tianyu Gao, Kai Li, and Danqi Chen

   NeurIPS 2022 Paper Code Poster
2. A Dataset Auditing Method for Collaboratively Trained Machine Learning Models

   Yangsibo Huang, Chun-Yin Huang, Xiaoxiao Li, and Kai Li

   IEEE Transactions on Medical Imaging 2022 Paper Code

2021

1. Evaluating Gradient Inversion Attacks and Defenses in Federated Learning

   Yangsibo Huang, Samyak Gupta, Zhao Song, Kai Li, and Sanjeev Arora

   NeurIPS 2021 (Oral) Paper Code Poster
2. EMA: Auditing Data Removal from Trained Models

   Yangsibo Huang, Xiaoxiao Li, and Kai Li

   MICCAI 2021 Paper Code
3. DeepMC: a deep learning method for efficient Monte Carlo beamlet dose calculation by predictive denoising in magnetic resonance-guided radiotherapy

   Ryan Neph, Qihui Lyu, Yangsibo Huang, You Ming Yang, and Ke Sheng

   Physics in Medicine & Biology 2021 Paper

2020

1. TextHide: Tackling Data Privacy in Language Understanding Tasks

   Yangsibo Huang, Zhao Song, Danqi Chen, Kai Li, and Sanjeev Arora

   EMNLP 2020 Paper Code
2. InstaHide: Instance-hiding Schemes for Private Distributed Learning

   Yangsibo Huang, Zhao Song, Kai Li, and Sanjeev Arora

   ICML 2020 Paper Code
3. Privacy-preserving learning via deep net pruning

   Yangsibo Huang, Yushan Su, Sachin Ravi, Zhao Song, Sanjeev Arora, and Kai Li

   Preprint 2020 Paper

2019

1. Deep Q learning Driven CT Pancreas Segmentation with Geometry-aware U-Net

   Yunze Man, Yangsibo Huang, Junyi Feng, Xi Li, and Fei Wu

   IEEE Transactions on Medical Imaging 2019 Paper