Подписаться
Sven Gowal
Sven Gowal
DeepMind
Подтвержден адрес электронной почты в домене deepmind.com
Название
Процитировано
Процитировано
Год
Competition-level code generation with alphacode
Y Li, D Choi, J Chung, N Kushman, J Schrittwieser, R Leblond, T Eccles, ...
Science 378 (6624), 1092-1097, 2022
11352022
Fixing data augmentation to improve adversarial robustness
SA Rebuffi, S Gowal, DA Calian, F Stimberg, O Wiles, T Mann
arXiv preprint arXiv:2103.01946, 2021
818*2021
On the effectiveness of interval bound propagation for training verifiably robust models
S Gowal, K Dvijotham, R Stanforth, R Bunel, C Qin, J Uesato, ...
arXiv preprint arXiv:1810.12715, 2018
758*2018
Challenges of real-world reinforcement learning: definitions, benchmarks and analysis
G Dulac-Arnold, N Levine, DJ Mankowitz, J Li, C Paduraru, S Gowal, ...
Machine Learning 110 (9), 2419-2468, 2021
715*2021
A Dual Approach to Scalable Verification of Deep Networks.
K Dvijotham, R Stanforth, S Gowal, TA Mann, P Kohli
UAI 1 (2), 3, 2018
4762018
Towards stable and efficient training of verifiably robust neural networks
H Zhang, H Chen, C Xiao, S Gowal, R Stanforth, B Li, D Boning, CJ Hsieh
arXiv preprint arXiv:1906.06316, 2019
3932019
Uncovering the limits of adversarial training against norm-bounded adversarial examples
S Gowal, C Qin, J Uesato, T Mann, P Kohli
arXiv preprint arXiv:2010.03593, 2020
3622020
Adversarial robustness through local linearization
C Qin, J Martens, S Gowal, D Krishnan, K Dvijotham, A Fawzi, S De, ...
Advances in neural information processing systems 32, 2019
3552019
A fine-grained analysis on distribution shift
O Wiles, S Gowal, F Stimberg, S Alvise-Rebuffi, I Ktena, K Dvijotham, ...
arXiv preprint arXiv:2110.11328, 2021
2512021
Achieving verified robustness to symbol substitutions via interval bound propagation
PS Huang, R Stanforth, J Welbl, C Dyer, D Yogatama, S Gowal, ...
arXiv preprint arXiv:1909.01492, 2019
1872019
Training verified learners with learned verifiers
K Dvijotham, S Gowal, R Stanforth, R Arandjelovic, B O'Donoghue, ...
arXiv preprint arXiv:1805.10265, 2018
1852018
An alternative surrogate loss for pgd-based adversarial testing
S Gowal, J Uesato, C Qin, PS Huang, T Mann, P Kohli
arXiv preprint arXiv:1910.09338, 2019
892019
Towards robust image classification using sequential attention models
D Zoran, M Chrzanowski, PS Huang, S Gowal, A Mott, P Kohli
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2020
802020
Evaluating the adversarial robustness of adaptive test-time defenses
F Croce, S Gowal, T Brunner, E Shelhamer, M Hein, T Cemgil
International Conference on Machine Learning, 4421-4435, 2022
792022
The autoencoding variational autoencoder
T Cemgil, S Ghaisas, K Dvijotham, S Gowal, P Kohli
Advances in Neural Information Processing Systems 33, 15077-15087, 2020
742020
Differentially private diffusion models generate useful synthetic images
S Ghalebikesabi, L Berrada, S Gowal, I Ktena, R Stanforth, J Hayes, S De, ...
arXiv preprint arXiv:2302.13861, 2023
682023
Generative models improve fairness of medical classifiers under distribution shifts
I Ktena, O Wiles, I Albuquerque, SA Rebuffi, R Tanno, AG Roy, S Azizi, ...
Nature Medicine, 1-8, 2024
642024
Achieving robustness in the wild via adversarial mixing with disentangled representations
S Gowal, C Qin, PS Huang, T Cemgil, K Dvijotham, T Mann, P Kohli
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020
642020
A framework for robustness certification of smoothed classifiers using f-divergences
KD Dvijotham, J Hayes, B Balle, Z Kolter, C Qin, A Gyorgy, K Xiao, ...
International Conference on Learning Representations, 2020
612020
Defending against image corruptions through adversarial augmentations
DA Calian, F Stimberg, O Wiles, SA Rebuffi, A Gyorgy, T Mann, S Gowal
arXiv preprint arXiv:2104.01086, 2021
522021
В данный момент система не может выполнить эту операцию. Повторите попытку позднее.
Статьи 1–20