Yangsibo Huang

69 papers A* 21Journal 43Unranked 5

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	An Adversarial Perspective on Machine Unlearning for AI Safety. Trans. Mach. Learn. Res. Jakub Lucki, Boyi Wei, Yangsibo Huang, Peter Henderson, Florian Tramèr, Javier Rando
2025	A*	`conf`	Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards. ICML Yangsibo Huang, Milad Nasr, Anastasios Nikolas Angelopoulos, Nicholas Carlini, Wei-Lin Chiang, Christopher A. Choquette-Choo, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Ken Liu, Ion Stoica, Florian Tramèr, Chiyuan Zhang
2025	J	`jnl`	Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards. CoRR Yangsibo Huang, Milad Nasr, Anastasios Angelopoulos, Nicholas Carlini, Wei-Lin Chiang, Christopher A. Choquette-Choo, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Ken Ziyu Liu, Ion Stoica, Florian Tramèr, Chiyuan Zhang
2025	A*	`conf`	Fantastic Copyrighted Beasts and How (Not) to Generate Them. ICLR Luxi He, Yangsibo Huang, Weijia Shi, Tinghao Xie, Haotian Liu, Yue Wang, Luke Zettlemoyer, Chiyuan Zhang, Danqi Chen, Peter Henderson
2025	A*	`conf`	GMValuator: Similarity-based Data Valuation for Generative Models. ICLR Jiaxi Yang, Wenlong Deng, Benlin Liu, Yangsibo Huang, James Zou, Xiaoxiao Li
2025	A*	`conf`	MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations. ICML Kaixuan Huang, Jiacheng Guo, Zihao Li, Xiang Ji, Jiawei Ge, Wenzhe Li, Yingqing Guo, Tianle Cai, Hui Yuan, Runzhe Wang, Yue Wu, Ming Yin, Shange Tang, Yangsibo Huang, Chi Jin, Xinyun Chen, Chiyuan Zhang, Mengdi Wang
2025	J	`jnl`	MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations. CoRR Kaixuan Huang, Jiacheng Guo, Zihao Li, Xiang Ji, Jiawei Ge, Wenzhe Li, Yingqing Guo, Tianle Cai, Hui Yuan, Runzhe Wang, Yue Wu, Ming Yin, Shange Tang, Yangsibo Huang, Chi Jin, Xinyun Chen, Chiyuan Zhang, Mengdi Wang
2025	A*	`conf`	MUSE: Machine Unlearning Six-Way Evaluation for Language Models. ICLR Weijia Shi, Jaechan Lee, Yangsibo Huang, Sadhika Malladi, Jieyu Zhao, Ari Holtzman, Daogao Liu, Luke Zettlemoyer, Noah A. Smith, Chiyuan Zhang
2025	A*	`conf`	On Evaluating the Durability of Safeguards for Open-Weight LLMs. ICLR Xiangyu Qi, Boyi Wei, Nicholas Carlini, Yangsibo Huang, Tinghao Xie, Luxi He, Matthew Jagielski, Milad Nasr, Prateek Mittal, Peter Henderson
2025	—	`conf`	On Memorization of Large Language Models in Logical Reasoning. IJCNLP-AACL (long papers) Chulin Xie, Yangsibo Huang, Chiyuan Zhang, Da Yu, Xinyun Chen, Bill Yuchen Lin, Bo Li, Badih Ghazi, Ravi Kumar
2025	J	`jnl`	Quantifying Cross-Modality Memorization in Vision-Language Models. CoRR Yuxin Wen, Yangsibo Huang, Tom Goldstein, Ravi Kumar, Badih Ghazi, Chiyuan Zhang
2025	A*	`conf`	SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal. ICLR Tinghao Xie, Xiangyu Qi, Yi Zeng, Yangsibo Huang, Udari Madhushani Sehwag, Kaixuan Huang, Luxi He, Boyi Wei, Dacheng Li, Ying Sheng, Ruoxi Jia, Bo Li, Kai Li, Danqi Chen, Peter Henderson, Prateek Mittal
2025	J	`jnl`	Scaling Embedding Layers in Language Models. CoRR Da Yu, Edith Cohen, Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Daogao Liu, Chiyuan Zhang
2025	A*	`conf`	Scaling Laws for Differentially Private Language Models. ICML Ryan McKenna, Yangsibo Huang, Amer Sinha, Borja Balle, Zachary Charles, Christopher A. Choquette-Choo, Badih Ghazi, Georgios Kaissis, Ravi Kumar, Ruibo Liu, Da Yu, Chiyuan Zhang
2025	J	`jnl`	Scaling Laws for Differentially Private Language Models. CoRR Ryan McKenna, Yangsibo Huang, Amer Sinha, Borja Balle, Zachary Charles, Christopher A. Choquette-Choo, Badih Ghazi, Georgios Kaissis, Ravi Kumar, Ruibo Liu, Da Yu, Chiyuan Zhang
2025	A*	`conf`	Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy. ICLR Yangsibo Huang, Daogao Liu, Lynn Chua, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Milad Nasr, Amer Sinha, Chiyuan Zhang
2025	J	`jnl`	VaultGemma: A Differentially Private Gemma Model. CoRR Amer Sinha, Thomas Mesnard, Ryan McKenna, Daogao Liu, Christopher A. Choquette-Choo, Yangsibo Huang, Da Yu, Georgios Kaissis, Zachary Charles, Ruibo Liu, Lynn Chua, Pritish Kamath, Pasin Manurangsi, Steve He, Chiyuan Zhang, Badih Ghazi, Borja de Balle Pigem, Prem Eruvbetine, Tris Warkentin, Armand Joulin, Ravi Kumar
2024	J	`jnl`	A Safe Harbor for AI Evaluation and Red Teaming. CoRR Shayne Longpre, Sayash Kapoor, Kevin Klyman, Ashwin Ramaswami, Rishi Bommasani, Borhane Blili-Hamelin, Yangsibo Huang, Aviya Skowron, Zheng Xin Yong, Suhas Kotha, Yi Zeng, Weiyan Shi, Xianjun Yang, Reid Southen, Alexander Robey, Patrick Chao, Diyi Yang, Ruoxi Jia, Daniel Kang, Sandy Pentland, Arvind Narayanan, Percy Liang, Peter Henderson
2024	J	`jnl`	AI Risk Management Should Incorporate Both Safety and Security. CoRR Xiangyu Qi, Yangsibo Huang, Yi Zeng, Edoardo Debenedetti, Jonas Geiping, Luxi He, Kaixuan Huang, Udari Madhushani, Vikash Sehwag, Weijia Shi, Boyi Wei, Tinghao Xie, Danqi Chen, Pin-Yu Chen, Jeffrey Ding, Ruoxi Jia, Jiaqi Ma, Arvind Narayanan, Weijie J. Su, Mengdi Wang, Chaowei Xiao, Bo Li, Dawn Song, Peter Henderson, Prateek Mittal
2024	J	`jnl`	An Adversarial Perspective on Machine Unlearning for AI Safety. CoRR Jakub Lucki, Boyi Wei, Yangsibo Huang, Peter Henderson, Florian Tramèr, Javier Rando
2024	A*	`conf`	Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications. ICML Boyi Wei, Kaixuan Huang, Yangsibo Huang, Tinghao Xie, Xiangyu Qi, Mengzhou Xia, Prateek Mittal, Mengdi Wang, Peter Henderson
2024	J	`jnl`	Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications. CoRR Boyi Wei, Kaixuan Huang, Yangsibo Huang, Tinghao Xie, Xiangyu Qi, Mengzhou Xia, Prateek Mittal, Mengdi Wang, Peter Henderson
2024	A*	`conf`	Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation. ICLR Yangsibo Huang, Samyak Gupta, Mengzhou Xia, Kai Li, Danqi Chen
2024	A*	`conf`	ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty. NeurIPS Xindi Wu, Dingli Yu, Yangsibo Huang, Olga Russakovsky, Sanjeev Arora
2024	J	`jnl`	ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty. CoRR Xindi Wu, Dingli Yu, Yangsibo Huang, Olga Russakovsky, Sanjeev Arora
2024	J	`jnl`	Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models. CoRR Lynn Chua, Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chulin Xie, Chiyuan Zhang
2024	A*	`conf`	Detecting Pretraining Data from Large Language Models. ICLR Weijia Shi, Anirudh Ajith, Mengzhou Xia, Yangsibo Huang, Daogao Liu, Terra Blevins, Danqi Chen, Luke Zettlemoyer
2024	A*	`conf`	Evaluating Copyright Takedown Methods for Language Models. NeurIPS Boyi Wei, Weijia Shi, Yangsibo Huang, Noah A. Smith, Chiyuan Zhang, Luke Zettlemoyer, Kai Li, Peter Henderson
2024	J	`jnl`	Evaluating Copyright Takedown Methods for Language Models. CoRR Boyi Wei, Weijia Shi, Yangsibo Huang, Noah A. Smith, Chiyuan Zhang, Luke Zettlemoyer, Kai Li, Peter Henderson
2024	J	`jnl`	Fantastic Copyrighted Beasts and How (Not) to Generate Them. CoRR Luxi He, Yangsibo Huang, Weijia Shi, Tinghao Xie, Haotian Liu, Yue Wang, Luke Zettlemoyer, Chiyuan Zhang, Danqi Chen, Peter Henderson
2024	A*	`conf`	LabelDP-Pro: Learning with Label Differential Privacy via Projections. ICLR Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Chiyuan Zhang
2024	J	`jnl`	MUSE: Machine Unlearning Six-Way Evaluation for Language Models. CoRR Weijia Shi, Jaechan Lee, Yangsibo Huang, Sadhika Malladi, Jieyu Zhao, Ari Holtzman, Daogao Liu, Luke Zettlemoyer, Noah A. Smith, Chiyuan Zhang
2024	J	`jnl`	Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice. CoRR A. Feder Cooper, Christopher A. Choquette-Choo, Miranda Bogen, Matthew Jagielski, Katja Filippova, Ken Ziyu Liu, Alexandra Chouldechova, Jamie Hayes, Yangsibo Huang, Niloofar Mireshghallah, Ilia Shumailov, Eleni Triantafillou, Peter Kairouz, Nicole Mitchell, Percy Liang, Daniel E. Ho, Yejin Choi, Sanmi Koyejo, Fernando A. Delgado, James Grimmelmann, Vitaly Shmatikov, Christopher De Sa, Solon Barocas, Amy Cyphert, Mark A. Lemley, danah boyd, Jennifer Wortman Vaughan, Miles Brundage, David Bau, Seth Neel, Abigail Z. Jacobs, Andreas Terzis, Hanna M. Wallach, Nicolas Papernot, Katherine Lee
2024	J	`jnl`	Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning. CoRR Lynn Chua, Badih Ghazi, Yangsibo Huang, Pritish Kamath, Daogao Liu, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang
2024	J	`jnl`	On Evaluating the Durability of Safeguards for Open-Weight LLMs. CoRR Xiangyu Qi, Boyi Wei, Nicholas Carlini, Yangsibo Huang, Tinghao Xie, Luxi He, Matthew Jagielski, Milad Nasr, Prateek Mittal, Peter Henderson
2024	J	`jnl`	On Memorization of Large Language Models in Logical Reasoning. CoRR Chulin Xie, Yangsibo Huang, Chiyuan Zhang, Da Yu, Xinyun Chen, Bill Yuchen Lin, Bo Li, Badih Ghazi, Ravi Kumar
2024	A*	`conf`	Position: A Safe Harbor for AI Evaluation and Red Teaming. ICML Shayne Longpre, Sayash Kapoor, Kevin Klyman, Ashwin Ramaswami, Rishi Bommasani, Borhane Blili-Hamelin, Yangsibo Huang, Aviya Skowron, Zheng Xin Yong, Suhas Kotha, Yi Zeng, Weiyan Shi, Xianjun Yang, Reid Southen, Alexander Robey, Patrick Chao, Diyi Yang, Ruoxi Jia, Daniel Kang, Sandy Pentland, Arvind Narayanan, Percy Liang, Peter Henderson
2024	J	`jnl`	SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors. CoRR Tinghao Xie, Xiangyu Qi, Yi Zeng, Yangsibo Huang, Udari Madhushani Sehwag, Kaixuan Huang, Luxi He, Boyi Wei, Dacheng Li, Ying Sheng, Ruoxi Jia, Bo Li, Kai Li, Danqi Chen, Peter Henderson, Prateek Mittal
2024	J	`jnl`	The Future of Open Human Feedback. CoRR Shachar Don-Yehiya, Ben Burtenshaw, Ramón Fernandez Astudillo, Cailean Osborne, Mimansa Jaiswal, Tzu-Sheng Kuo, Wenting Zhao, Idan Shenfeld, Andi Peng, Mikhail Yurochkin, Atoosa Kasirzadeh, Yangsibo Huang, Tatsunori Hashimoto, Yacine Jernite, Daniel Vila-Suero, Omri Abend, Jennifer Ding, Sara Hooker, Hannah Rose Kirk, Leshem Choshen
2024	J	`jnl`	Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy. CoRR Yangsibo Huang, Daogao Liu, Lynn Chua, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Milad Nasr, Amer Sinha, Chiyuan Zhang
2023	J	`jnl`	A Dataset Auditing Method for Collaboratively Trained Machine Learning Models. IEEE Trans. Medical Imaging Yangsibo Huang, Chun-Yin Huang, Xiaoxiao Li, Kai Li
2023	J	`jnl`	Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation. CoRR Yangsibo Huang, Samyak Gupta, Mengzhou Xia, Kai Li, Danqi Chen
2023	J	`jnl`	Challenges towards the Next Frontier in Privacy. CoRR Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Matthew Jagielski, Yangsibo Huang, Peter Kairouz, Gautam Kamath, Sewoong Oh, Olga Ohrimenko, Nicolas Papernot, Ryan Rogers, Milan Shen, Shuang Song, Weijie J. Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Sergey Yekhanin, Da Yu, Huanyu Zhang, Wanrong Zhang
2023	J	`jnl`	Detecting Pretraining Data from Large Language Models. CoRR Weijia Shi, Anirudh Ajith, Mengzhou Xia, Yangsibo Huang, Daogao Liu, Terra Blevins, Danqi Chen, Luke Zettlemoyer
2023	J	`jnl`	Learning across Data Owners with Joint Differential Privacy. CoRR Yangsibo Huang, Haotian Jiang, Daogao Liu, Mohammad Mahdian, Jieming Mao, Vahab Mirrokni
2023	J	`jnl`	Matching-based Data Valuation for Generative Model. CoRR Jiaxi Yang, Wenglong Deng, Benlin Liu, Yangsibo Huang, Xiaoxiao Li
2023	A*	`conf`	Privacy Implications of Retrieval-Based Language Models. EMNLP Yangsibo Huang, Samyak Gupta, Zexuan Zhong, Kai Li, Danqi Chen
2023	J	`jnl`	Privacy Implications of Retrieval-Based Language Models. CoRR Yangsibo Huang, Samyak Gupta, Zexuan Zhong, Kai Li, Danqi Chen
2023	A*	`conf`	Sparsity-Preserving Differentially Private Training of Large Embedding Models. NeurIPS Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang
2023	J	`jnl`	Sparsity-Preserving Differentially Private Training of Large Embedding Models. CoRR Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang
2023	J	`jnl`	kNN-Adapter: Efficient Domain Adaptation for Black-Box Language Models. CoRR Yangsibo Huang, Daogao Liu, Zexuan Zhong, Weijia Shi, Yin Tat Lee
2022	A*	`conf`	Recovering Private Text in Federated Learning of Language Models. NeurIPS Samyak Gupta, Yangsibo Huang, Zexuan Zhong, Tianyu Gao, Kai Li, Danqi Chen
2022	J	`jnl`	Recovering Private Text in Federated Learning of Language Models. CoRR Samyak Gupta, Yangsibo Huang, Zexuan Zhong, Tianyu Gao, Kai Li, Danqi Chen
2021	—	`conf`	EMA: Auditing Data Removal from Trained Models. MICCAI (5) Yangsibo Huang, Xiaoxiao Li, Kai Li
2021	J	`jnl`	EMA: Auditing Data Removal from Trained Models. CoRR Yangsibo Huang, Xiaoxiao Li, Kai Li
2021	A*	`conf`	Evaluating Gradient Inversion Attacks and Defenses in Federated Learning. NeurIPS Yangsibo Huang, Samyak Gupta, Zhao Song, Kai Li, Sanjeev Arora
2021	J	`jnl`	Evaluating Gradient Inversion Attacks and Defenses in Federated Learning. CoRR Yangsibo Huang, Samyak Gupta, Zhao Song, Kai Li, Sanjeev Arora
2020	J	`jnl`	Deep Learning Based Detection and Localization of Cerebal Aneurysms in Computed Tomography Angiography. CoRR Ziheng Duan, Daniel Montes, Yangsibo Huang, Dufan Wu, Javier M. Romero, Ramon Gilberto Gonzalez, Quanzheng Li
2020	—	`conf`	IFGAN: Missing Value Imputation using Feature-specific Generative Adversarial Networks. IEEE BigData Wei Qiu, Yangsibo Huang, Quanzheng Li
2020	J	`jnl`	IFGAN: Missing Value Imputation using Feature-specific Generative Adversarial Networks. CoRR Wei Qiu, Yangsibo Huang, Quanzheng Li
2020	A*	`conf`	InstaHide: Instance-hiding Schemes for Private Distributed Learning. ICML Yangsibo Huang, Zhao Song, Kai Li, Sanjeev Arora
2020	J	`jnl`	InstaHide: Instance-hiding Schemes for Private Distributed Learning. CoRR Yangsibo Huang, Zhao Song, Kai Li, Sanjeev Arora
2020	J	`jnl`	MixCon: Adjusting the Separability of Data Representations for Harder Data Recovery. CoRR Xiaoxiao Li, Yangsibo Huang, Binghui Peng, Zhao Song, Kai Li
2020	J	`jnl`	Privacy-preserving Learning via Deep Net Pruning. CoRR Yangsibo Huang, Yushan Su, Sachin Ravi, Zhao Song, Sanjeev Arora, Kai Li
2020	—	`conf`	TextHide: Tackling Data Privacy for Language Understanding Tasks. EMNLP (Findings) Yangsibo Huang, Zhao Song, Danqi Chen, Kai Li, Sanjeev Arora
2020	J	`jnl`	TextHide: Tackling Data Privacy in Language Understanding Tasks. CoRR Yangsibo Huang, Zhao Song, Danqi Chen, Kai Li, Sanjeev Arora
2019	J	`jnl`	Deep Q Learning Driven CT Pancreas Segmentation With Geometry-Aware U-Net. IEEE Trans. Medical Imaging Yunze Man, Yangsibo Huang, Junyi Feng, Xi Li, Fei Wu
2019	J	`jnl`	Deep Q Learning Driven CT Pancreas Segmentation with Geometry-Aware U-Net. CoRR Yunze Man, Yangsibo Huang, Junyi Feng, Xi Li, Fei Wu
2019	—	`conf`	DeepMCDose: A Deep Learning Method for Efficient Monte Carlo Beamlet Dose Calculation by Predictive Denoising in MR-Guided Radiotherapy. AIRT@MICCAI Ryan Neph, Yangsibo Huang, Youming Yang, Ke Sheng