Jonathan Hayase

37 papers A* 12Journal 24Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model. CoRR Jacqueline He, Jonathan Hayase, Wen-tau Yih, Sewoong Oh, Luke Zettlemoyer, Pang Wei Koh
2026	J	`jnl`	Are you going to finish that? A Practical Study of the Tokenization Boundary Problem. CoRR Hao Xu, Alisa Liu, Jonathan Hayase, Yejin Choi, Noah A. Smith
2025	J	`jnl`	Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations. CoRR Brian Siyuan Zheng, Alisa Liu, Orevaoghene Ahia, Jonathan Hayase, Yejin Choi, Noah A. Smith
2025	A*	`conf`	PLeaS - Merging Models with Permutations and Least Squares. CVPR Anshul Nasery, Jonathan Hayase, Pang Wei Koh, Sewoong Oh
2025	J	`jnl`	Sampling from Your Language Model One Byte at a Time. CoRR Jonathan Hayase, Alisa Liu, Noah A. Smith, Sewoong Oh
2025	A*	`conf`	Scalable Extraction of Training Data from Aligned, Production Language Models. ICLR Milad Nasr, Javier Rando, Nicholas Carlini, Jonathan Hayase, Matthew Jagielski, A. Feder Cooper, Daphne Ippolito, Christopher A. Choquette-Choo, Florian Tramèr, Katherine Lee
2025	J	`jnl`	Scalable Fingerprinting of Large Language Models. CoRR Anshul Nasery, Jonathan Hayase, Creston Brooks, Peiyao Sheng, Himanshu Tyagi, Pramod Viswanath, Sewoong Oh
2025	J	`jnl`	SuperBPE: Space Travel for Language Models. CoRR Alisa Liu, Jonathan Hayase, Valentin Hofmann, Sewoong Oh, Noah A. Smith, Yejin Choi
2024	A*	`conf`	Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions. NeurIPS Jonathan Hayase, Alisa Liu, Yejin Choi, Sewoong Oh, Noah A. Smith
2024	J	`jnl`	Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data? CoRR Jonathan Hayase, Alisa Liu, Yejin Choi, Sewoong Oh, Noah A. Smith
2024	A*	`conf`	Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares Extended Abstract. COLT Gavin Brown, Jonathan Hayase, Samuel B. Hopkins, Weihao Kong, Xiyang Liu, Sewoong Oh, Juan C. Perdomo, Adam Smith
2024	J	`jnl`	Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares. CoRR Gavin Brown, Jonathan Hayase, Samuel B. Hopkins, Weihao Kong, Xiyang Liu, Sewoong Oh, Juan C. Perdomo, Adam Smith
2024	J	`jnl`	Monge-Kantorovich Fitting With Sobolev Budgets. CoRR Forest Kobayashi, Jonathan Hayase, Young-Heon Kim
2024	J	`jnl`	OML: Open, Monetizable, and Loyal AI. CoRR Zerui Cheng, Edoardo Contente, Ben Finch, Oleg Golev, Jonathan Hayase, Andrew Miller, Niusha Moshrefi, Anshul Nasery, Sandeep Nailwal, Sewoong Oh, Himanshu Tyagi, Pramod Viswanath
2024	J	`jnl`	OML: Open, Monetizable, and Loyal AI. IACR Cryptol. ePrint Arch. Zerui Cheng, Edoardo Contente, Ben Finch, Oleg Golev, Jonathan Hayase, Andrew Miller, Niusha Moshrefi, Anshul Nasery, Sandeep Nailwal, Sewoong Oh, Himanshu Tyagi, Pramod Viswanath
2024	J	`jnl`	PLeaS - Merging Models with Permutations and Least Squares. CoRR Anshul Nasery, Jonathan Hayase, Pang Wei Koh, Sewoong Oh
2024	A*	`conf`	Query-Based Adversarial Prompt Generation. NeurIPS Jonathan Hayase, Ema Borevkovic, Nicholas Carlini, Florian Tramèr, Milad Nasr
2024	J	`jnl`	Query-Based Adversarial Prompt Generation. CoRR Jonathan Hayase, Ema Borevkovic, Nicholas Carlini, Florian Tramèr, Milad Nasr
2024	J	`jnl`	Stealing Part of a Production Language Model. CoRR Nicholas Carlini, Daniel Paleka, Krishnamurthy (Dj) Dvijotham, Thomas Steinke, Jonathan Hayase, A. Feder Cooper, Katherine Lee, Matthew Jagielski, Milad Nasr, Arthur Conmy, Eric Wallace, David Rolnick, Florian Tramèr
2024	A*	`conf`	Stealing part of a production language model. ICML Nicholas Carlini, Daniel Paleka, Krishnamurthy Dj Dvijotham, Thomas Steinke, Jonathan Hayase, A. Feder Cooper, Katherine Lee, Matthew Jagielski, Milad Nasr, Arthur Conmy, Eric Wallace, David Rolnick, Florian Tramèr
2023	A*	`conf`	DataComp: In search of the next generation of multimodal datasets. NeurIPS Samir Yitzhak Gadre, Gabriel Ilharco, Alex Fang, Jonathan Hayase, Georgios Smyrnis, Thao Nguyen, Ryan Marten, Mitchell Wortsman, Dhruba Ghosh, Jieyu Zhang, Eyal Orgad, Rahim Entezari, Giannis Daras, Sarah M. Pratt, Vivek Ramanujan, Yonatan Bitton, Kalyani Marathe, Stephen Mussmann, Richard Vencu, Mehdi Cherti, Ranjay Krishna, Pang Wei Koh, Olga Saukh, Alexander J. Ratner, Shuran Song, Hannaneh Hajishirzi, Ali Farhadi, Romain Beaumont, Sewoong Oh, Alex Dimakis, Jenia Jitsev, Yair Carmon, Vaishaal Shankar, Ludwig Schmidt
2023	J	`jnl`	DataComp: In search of the next generation of multimodal datasets. CoRR Samir Yitzhak Gadre, Gabriel Ilharco, Alex Fang, Jonathan Hayase, Georgios Smyrnis, Thao Nguyen, Ryan Marten, Mitchell Wortsman, Dhruba Ghosh, Jieyu Zhang, Eyal Orgad, Rahim Entezari, Giannis Daras, Sarah M. Pratt, Vivek Ramanujan, Yonatan Bitton, Kalyani Marathe, Stephen Mussmann, Richard Vencu, Mehdi Cherti, Ranjay Krishna, Pang Wei Koh, Olga Saukh, Alexander Ratner, Shuran Song, Hannaneh Hajishirzi, Ali Farhadi, Romain Beaumont, Sewoong Oh, Alex Dimakis, Jenia Jitsev, Yair Carmon, Vaishaal Shankar, Ludwig Schmidt
2023	A*	`conf`	Few-shot Backdoor Attacks via Neural Tangent Kernels. ICLR Jonathan Hayase, Sewoong Oh
2023	A*	`conf`	Git Re-Basin: Merging Models modulo Permutation Symmetries. ICLR Samuel K. Ainsworth, Jonathan Hayase, Siddhartha S. Srinivasa
2023	A*	`conf`	Label Poisoning is All You Need. NeurIPS Rishi D. Jha, Jonathan Hayase, Sewoong Oh
2023	J	`jnl`	Label Poisoning is All You Need. CoRR Rishi D. Jha, Jonathan Hayase, Sewoong Oh
2023	J	`jnl`	Scalable Extraction of Training Data from (Production) Language Models. CoRR Milad Nasr, Nicholas Carlini, Jonathan Hayase, Matthew Jagielski, A. Feder Cooper, Daphne Ippolito, Christopher A. Choquette-Choo, Eric Wallace, Florian Tramèr, Katherine Lee
2023	J	`jnl`	Towards a Defense Against Federated Backdoor Attacks Under Continuous Training. Trans. Mach. Learn. Res. Shuaiqi Wang, Jonathan Hayase, Giulia Fanti, Sewoong Oh
2022	J	`jnl`	Few-shot Backdoor Attacks via Neural Tangent Kernels. CoRR Jonathan Hayase, Sewoong Oh
2022	J	`jnl`	Git Re-Basin: Merging Models modulo Permutation Symmetries. CoRR Samuel K. Ainsworth, Jonathan Hayase, Siddhartha S. Srinivasa
2022	J	`jnl`	Towards a Defense against Backdoor Attacks in Continual Federated Learning. CoRR Shuaiqi Wang, Jonathan Hayase, Giulia Fanti, Sewoong Oh
2022	A*	`conf`	Zonotope Domains for Lagrangian Neural Network Verification. NeurIPS Matt Jordan, Jonathan Hayase, Alex Dimakis, Sewoong Oh
2022	J	`jnl`	Zonotope Domains for Lagrangian Neural Network Verification. CoRR Matt Jordan, Jonathan Hayase, Alexandros G. Dimakis, Sewoong Oh
2021	A*	`conf`	Defense against backdoor attacks via robust covariance estimation. ICML Jonathan Hayase, Weihao Kong, Raghav Somani, Sewoong Oh
2021	J	`jnl`	SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics. CoRR Jonathan Hayase, Weihao Kong, Raghav Somani, Sewoong Oh
2019	—	`conf`	The Futility of Bias-Free Learning and Search. Australasian Conference on Artificial Intelligence George D. Montañez, Jonathan Hayase, Julius Lauw, Dominique Macias, Akshay Trikha, Julia Vendemiatti
2019	J	`jnl`	The Futility of Bias-Free Learning and Search. CoRR George D. Montañez, Jonathan Hayase, Julius Lauw, Dominique Macias, Akshay Trikha, Julia Vendemiatti