Подписаться
Borja Balle
Borja Balle
DeepMind
Подтвержден адрес электронной почты в домене google.com - Главная страница
Название
Процитировано
Процитировано
Год
Ethical and social risks of harm from language models
L Weidinger, J Mellor, M Rauh, C Griffin, J Uesato, PS Huang, M Cheng, ...
arXiv preprint arXiv:2112.04359, 2021
9162021
Taxonomy of risks posed by language models
L Weidinger, J Uesato, M Rauh, C Griffin, PS Huang, J Mellor, A Glaese, ...
Proceedings of the 2022 ACM Conference on Fairness, Accountability, and …, 2022
5522022
Extracting training data from diffusion models
N Carlini, J Hayes, M Nasr, M Jagielski, V Sehwag, F Tramer, B Balle, ...
32nd USENIX Security Symposium (USENIX Security 23), 5253-5270, 2023
5502023
Improving the gaussian mechanism for differential privacy: Analytical calibration and optimal denoising
B Balle, YX Wang
International Conference on Machine Learning, 394-403, 2018
4752018
Privacy amplification by subsampling: Tight analyses via couplings and divergences
B Balle, G Barthe, M Gaboardi
Advances in neural information processing systems 31, 2018
4152018
Subsampled rényi differential privacy and analytical moments accountant
YX Wang, B Balle, SP Kasiviswanathan
The 22nd international conference on artificial intelligence and statistics …, 2019
4092019
Privacy-preserving distributed linear regression on high-dimensional data
A Gascón, P Schoppmann, B Balle, M Raykova, J Doerner, S Zahur, ...
Cryptology ePrint Archive, 2016
375*2016
Model-agnostic counterfactual explanations for consequential decisions
AH Karimi, G Barthe, B Balle, I Valera
International conference on artificial intelligence and statistics, 895-905, 2020
3742020
The privacy blanket of the shuffle model
B Balle, J Bell, A Gascón, K Nissim
Advances in Cryptology–CRYPTO 2019: 39th Annual International Cryptology …, 2019
2972019
Unlocking high-accuracy differentially private image classification through scale
S De, L Berrada, J Hayes, SL Smith, B Balle
arXiv preprint arXiv:2204.13650, 2022
1902022
Reconstructing training data with informed adversaries
B Balle, G Cherubin, J Hayes
2022 IEEE Symposium on Security and Privacy (SP), 1138-1156, 2022
1552022
Privacy-and utility-preserving textual analysis via calibrated multivariate perturbations
O Feyisetan, B Balle, T Drake, T Diethe
Proceedings of the 13th international conference on web search and data …, 2020
1382020
Private summation in the multi-message shuffle model
B Balle, J Bell, A Gascón, K Nissim
Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications …, 2020
1182020
Hypothesis testing interpretations and renyi differential privacy
B Balle, G Barthe, M Gaboardi, J Hsu, T Sato
International Conference on Artificial Intelligence and Statistics, 2496-2506, 2020
1152020
Spectral learning of weighted automata: A forward-backward perspective
B Balle, X Carreras, FM Luque, A Quattoni
Machine learning 96, 33-63, 2014
1022014
Continual learning in practice
T Diethe, T Borchert, E Thereska, B Balle, N Lawrence
arXiv preprint arXiv:1903.05202, 2019
902019
Privacy amplification via random check-ins
B Balle, P Kairouz, B McMahan, O Thakkar, A Guha Thakurta
Advances in Neural Information Processing Systems 33, 4623-4634, 2020
842020
Spectral learning of general weighted automata via constrained matrix completion
B Balle, M Mohri
Advances in neural information processing systems 25, 2012
762012
Learning weighted automata
B Balle, M Mohri
International Conference on Algebraic Informatics, 1-21, 2015
692015
Ethical and social risks of harm from language models. arXiv
L Weidinger, J Mellor, M Rauh, C Griffin, J Uesato, PS Huang, M Cheng, ...
arXiv preprint arXiv:2112.04359 10, 2021
662021
В данный момент система не может выполнить эту операцию. Повторите попытку позднее.
Статьи 1–20