Folgen
Aleksander Mądry
Aleksander Mądry
MIT
Bestätigte E-Mail-Adresse bei mit.edu - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Towards deep learning models resistant to adversarial attacks
A Madry, A Makelov, L Schmidt, D Tsipras, A Vladu
Proceedings of the International Conference on Representation Learning (ICLR …, 2018
130722018
How does batch normalization help optimization?
S Santurkar, D Tsipras, A Ilyas, A Madry
Advances in neural information processing systems 31, 2018
21872018
Adversarial examples are not bugs, they are features
A Ilyas, S Santurkar, D Tsipras, L Engstrom, B Tran, A Madry
Advances in neural information processing systems 32, 2019
20612019
Robustness may be at odds with accuracy
D Tsipras, S Santurkar, L Engstrom, A Turner, A Madry
Proceedings of the International Conference on Representation Learning (ICLR …, 2019
19532019
On evaluating adversarial robustness
N Carlini, A Athalye, N Papernot, W Brendel, J Rauber, D Tsipras, ...
arXiv preprint arXiv:1902.06705, 2019
10012019
On adaptive attacks to adversarial example defenses
F Tramer, N Carlini, W Brendel, A Madry
Advances in neural information processing systems 33, 1633-1645, 2020
8952020
Exploring the landscape of spatial robustness
L Engstrom, B Tran, D Tsipras, L Schmidt, A Madry
International conference on machine learning, 1802-1811, 2019
882*2019
Adversarially robust generalization requires more data
L Schmidt, S Santurkar, D Tsipras, K Talwar, A Madry
Advances in neural information processing systems 31, 2018
8702018
Spectral signatures in backdoor attacks
B Tran, J Li, A Madry
Advances in neural information processing systems 31, 2018
8352018
Do adversarially robust imagenet models transfer better?
H Salman, A Ilyas, L Engstrom, A Kapoor, A Madry
Advances in Neural Information Processing Systems 33, 3533-3545, 2020
4372020
Prior convictions: Black-box adversarial attacks with bandits and priors
A Ilyas, L Engstrom, A Madry
arXiv preprint arXiv:1807.07978, 2018
4322018
Electrical flows, laplacian systems, and faster approximation of maximum flow in undirected graphs
P Christiano, JA Kelner, A Madry, DA Spielman, SH Teng
Proceedings of the forty-third annual ACM symposium on Theory of computing …, 2011
4172011
Noise or signal: The role of image backgrounds in object recognition
K Xiao, L Engstrom, A Ilyas, A Madry
arXiv preprint arXiv:2006.09994, 2020
3762020
Label-consistent backdoor attacks
A Turner, D Tsipras, A Madry
arXiv preprint arXiv:1912.02771, 2019
3712019
Navigating central path with electrical flows: From flows to matchings, and back
A Madry
2013 IEEE 54th Annual Symposium on Foundations of Computer Science, 253-262, 2013
3022013
Implementation matters in deep rl: A case study on ppo and trpo
L Engstrom, A Ilyas, S Santurkar, D Tsipras, F Janoos, L Rudolph, ...
International conference on learning representations, 2019
2852019
An O(log n/log log n)-Approximation Algorithm for the Asymmetric Traveling Salesman Problem
A Asadpour, MX Goemans, A Mądry, SO Gharan, A Saberi
Operations Research 65 (4), 1043-1061, 2017
2642017
Adversarial robustness as a prior for learned representations
L Engstrom, A Ilyas, S Santurkar, D Tsipras, B Tran, A Madry
arXiv preprint arXiv:1906.00945, 2019
261*2019
Implementation matters in deep policy gradients: A case study on ppo and trpo
L Engstrom, A Ilyas, S Santurkar, D Tsipras, F Janoos, L Rudolph, ...
arXiv preprint arXiv:2005.12729, 2020
2342020
Image synthesis with a single (robust) classifier
S Santurkar, A Ilyas, D Tsipras, L Engstrom, B Tran, A Madry
Advances in Neural Information Processing Systems 32, 2019
230*2019
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20