关注
Hengrui Jia
Hengrui Jia
University of Toronto and Vector Institute
在 mail.utoronto.ca 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
Machine unlearning
L Bourtoule, V Chandrasekaran, CA Choquette-Choo, H Jia, A Travers, ...
2021 IEEE Symposium on Security and Privacy (SP), 141-159, 2021
6402021
Entangled watermarks as a defense against model extraction
H Jia, CA Choquette-Choo, V Chandrasekaran, N Papernot
30th USENIX security symposium (USENIX Security 21), 1937-1954, 2021
2352021
On the necessity of auditable algorithmic definitions for machine unlearning
A Thudi, H Jia, I Shumailov, N Papernot
31st USENIX Security Symposium (USENIX Security 22), 4007-4022, 2022
1032022
Proof-of-learning: Definitions and practice
H Jia, M Yaghini, CA Choquette-Choo, N Dullerud, A Thudi, ...
2021 IEEE Symposium on Security and Privacy (SP), 1039-1056, 2021
862021
A zest of lime: Towards architecture-independent model distances
H Jia, H Chen, J Guan, AS Shamsabadi, N Papernot
International Conference on Learning Representations, 2021
202021
SoK: Machine learning governance
V Chandrasekaran, H Jia, A Thudi, A Travers, M Yaghini, N Papernot
arXiv preprint arXiv:2109.10870, 2021
202021
Proof-of-learning is currently more broken than you think
C Fang, H Jia, A Thudi, M Yaghini, CA Choquette-Choo, N Dullerud, ...
2023 IEEE 8th European Symposium on Security and Privacy (EuroS&P), 797-816, 2023
16*2023
Attention, novelty preference and the visual paired comparison task
M Eizenman, J Chung, MH Yu, H Jia, P Jiang
Experimental eye research 183, 52-56, 2019
42019
LLM Dataset Inference: Did you train on my dataset?
P Maini, H Jia, N Papernot, A Dziedzic
arXiv preprint arXiv:2406.06443, 2024
12024
Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
A Thudi, H Jia, C Meehan, I Shumailov, N Papernot
arXiv preprint arXiv:2307.00310, 2023
2023
Finding Private Bugs: Debugging Implementations of Differentially Private Stochastic Gradient Descent
C Fang, H Jia, AS Shamsabadi, N Papernot
系统目前无法执行此操作,请稍后再试。
文章 1–11