Jonathan Hayase

According to our database, Jonathan Hayase authored at least 25 papers between 2019 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2025

Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations.

Brian Siyuan Zheng, Alisa Liu, Orevaoghene Ahia, Jonathan Hayase, Yejin Choi, Noah A. Smith

CoRR, June, 2025

Sampling from Your Language Model One Byte at a Time.

Jonathan Hayase, Alisa Liu, Noah A. Smith, Sewoong Oh

CoRR, June, 2025

SuperBPE: Space Travel for Language Models.

Alisa Liu, Jonathan Hayase, Valentin Hofmann, Sewoong Oh, Noah A. Smith, Yejin Choi

CoRR, March, 2025

Scalable Fingerprinting of Large Language Models.

Anshul Nasery, Jonathan Hayase, Creston Brooks, Peiyao Sheng, Himanshu Tyagi, Pramod Viswanath, Sewoong Oh

CoRR, February, 2025

Scalable Extraction of Training Data from Aligned, Production Language Models.

Milad Nasr, Javier Rando, Nicholas Carlini, Jonathan Hayase, Matthew Jagielski, A. Feder Cooper, Daphne Ippolito, Christopher A. Choquette-Choo, Florian Tramèr, Katherine Lee

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

PLeaS - Merging Models with Permutations and Least Squares.

Anshul Nasery, Jonathan Hayase, Pang Wei Koh, Sewoong Oh

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024

OML: Open, Monetizable, and Loyal AI.

Zerui Cheng, Edoardo Contente, Ben Finch, Oleg Golev, Jonathan Hayase, Andrew Miller, Niusha Moshrefi, Anshul Nasery, Sandeep Nailwal, Sewoong Oh, Himanshu Tyagi, Pramod Viswanath

IACR Cryptol. ePrint Arch., 2024

Monge-Kantorovich Fitting With Sobolev Budgets.

Forest Kobayashi, Jonathan Hayase, Young-Heon Kim

CoRR, 2024

Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?

Jonathan Hayase, Alisa Liu, Yejin Choi, Sewoong Oh, Noah A. Smith

CoRR, 2024

Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares.

Gavin Brown, Jonathan Hayase, Samuel B. Hopkins, Weihao Kong, Xiyang Liu, Sewoong Oh, Juan C. Perdomo, Adam Smith

CoRR, 2024

Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions.

Jonathan Hayase, Alisa Liu, Yejin Choi, Sewoong Oh, Noah A. Smith

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Query-Based Adversarial Prompt Generation.

Jonathan Hayase, Ema Borevkovic, Nicholas Carlini, Florian Tramèr, Milad Nasr

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Stealing part of a production language model.

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

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares Extended Abstract.

Gavin Brown, Jonathan Hayase, Samuel B. Hopkins, Weihao Kong, Xiyang Liu, Sewoong Oh, Juan C. Perdomo, Adam Smith

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

2023

Towards a Defense Against Federated Backdoor Attacks Under Continuous Training.

Shuaiqi Wang, Jonathan Hayase, Giulia Fanti, Sewoong Oh

Trans. Mach. Learn. Res., 2023

Scalable Extraction of Training Data from (Production) Language Models.

Milad Nasr, Nicholas Carlini, Jonathan Hayase, Matthew Jagielski, A. Feder Cooper, Daphne Ippolito, Christopher A. Choquette-Choo, Eric Wallace, Florian Tramèr, Katherine Lee

CoRR, 2023

Label Poisoning is All You Need.

Rishi D. Jha, Jonathan Hayase, Sewoong Oh

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

DataComp: In search of the next generation of multimodal datasets.

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

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Few-shot Backdoor Attacks via Neural Tangent Kernels.

Jonathan Hayase, Sewoong Oh

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Git Re-Basin: Merging Models modulo Permutation Symmetries.

Samuel K. Ainsworth, Jonathan Hayase, Siddhartha S. Srinivasa

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Towards a Defense against Backdoor Attacks in Continual Federated Learning.

Shuaiqi Wang, Jonathan Hayase, Giulia Fanti, Sewoong Oh

CoRR, 2022

Zonotope Domains for Lagrangian Neural Network Verification.

Matt Jordan, Jonathan Hayase, Alex Dimakis, Sewoong Oh

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics.

Jonathan Hayase, Weihao Kong, Raghav Somani, Sewoong Oh

CoRR, 2021

Defense against backdoor attacks via robust covariance estimation.

Jonathan Hayase, Weihao Kong, Raghav Somani, Sewoong Oh

Proceedings of the 38th International Conference on Machine Learning, 2021

2019

The Futility of Bias-Free Learning and Search.

George D. Montañez, Jonathan Hayase, Julius Lauw, Dominique Macias, Akshay Trikha, Julia Vendemiatti

Proceedings of the AI 2019: Advances in Artificial Intelligence, 2019