Follow
Jonathan Hayase
Jonathan Hayase
Verified email at cs.washington.edu - Homepage
Title
Cited by
Cited by
Year
Git Re-Basin: Merging Models modulo Permutation Symmetries
SK Ainsworth, J Hayase, S Srinivasa
The Eleventh International Conference on Learning Representations, 2022
1682022
SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics
J Hayase, W Kong, R Somani, S Oh
International Conference on Machine Learning, 4129-4139, 2021
134*2021
Datacomp: In search of the next generation of multimodal datasets
SY Gadre, G Ilharco, A Fang, J Hayase, G Smyrnis, T Nguyen, R Marten, ...
Advances in Neural Information Processing Systems 36, 2024
1192024
Scalable Extraction of Training Data from (Production) Language Models
M Nasr, N Carlini, J Hayase, M Jagielski, AF Cooper, D Ippolito, ...
arXiv preprint arXiv:2311.17035, 2023
672023
Few-shot Backdoor Attacks via Neural Tangent Kernels
J Hayase, S Oh
The Eleventh International Conference on Learning Representations, 2022
162022
The futility of bias-free learning and search
GD Montañez, J Hayase, J Lauw, D Macias, A Trikha, J Vendemiatti
Australasian Joint Conference on Artificial Intelligence, 277-288, 2019
142019
Label poisoning is all you need
R Jha, J Hayase, S Oh
Advances in Neural Information Processing Systems 36, 2024
82024
Towards a Defense Against Federated Backdoor Attacks Under Continuous Training
S Wang, J Hayase, G Fanti, S Oh
Transactions on Machine Learning Research, 2023
5*2023
Query-Based Adversarial Prompt Generation
J Hayase, E Borevkovic, N Carlini, F Tramèr, M Nasr
arXiv preprint arXiv:2402.12329, 2024
22024
Zonotope Domains for Lagrangian Neural Network Verification
M Jordan, J Hayase, A Dimakis, S Oh
Advances in Neural Information Processing Systems 35, 8400-8413, 2022
22022
Stealing Part of a Production Language Model
N Carlini, D Paleka, KD Dvijotham, T Steinke, J Hayase, AF Cooper, ...
arXiv preprint arXiv:2403.06634, 2024
2024
The system can't perform the operation now. Try again later.
Articles 1–11