Saeed Mahloujifar
Saeed Mahloujifar
Geverifieerd e-mailadres voor princeton.edu - Homepage
Titel
Geciteerd door
Geciteerd door
Jaar
The curse of concentration in robust learning: Evasion and poisoning attacks from concentration of measure
S Mahloujifar, DI Diochnos, M Mahmoody
Proceedings of the AAAI Conference on Artificial Intelligence 33, 4536-4543, 2019
812019
Adversarial risk and robustness: General definitions and implications for the uniform distribution
DI Diochnos, S Mahloujifar, M Mahmoody
arXiv preprint arXiv:1810.12272, 2018
322018
Can Adversarially Robust Learning Leverage Computational Hardness?
S Mahloujifar, M Mahmoody
[edit] Saeed Mahloujifar, Mohammad Mahmoody ; Proceedings of the 30th …, 2019
282019
Universal Multi-party Poisoning Attacks
S Mahloujifar, M Mahmoody, A Mohammed
Proceedings of the 36th International Conference on Machine Learning, PMLR …, 2019
23*2019
Blockwise p-Tampering Attacks on Cryptographic Primitives, Extractors, and Learners
S Mahloujifar, M Mahmoody
Theory of Cryptography Conference, 245-279, 2017
202017
Learning under -Tampering Attacks
S Mahloujifar, DI Diochnos, M Mahmoody
Proceedings of Algorithmic Learning Theory, PMLR 83:572-596, 2018., 2018
192018
An Attack on InstaHide: Is Private Learning Possible with Instance Encoding?
N Carlini, S Deng, S Garg, S Jha, S Mahloujifar, M Mahmoody, S Song, ...
arXiv preprint arXiv:2011.05315, 2020
122020
Lower bounds for adversarially robust pac learning
DI Diochnos, S Mahloujifar, M Mahmoody
arXiv preprint arXiv:1906.05815, 2019
102019
Computational concentration of measure: Optimal bounds, reductions, and more
O Etesami, S Mahloujifar, M Mahmoody
Proceedings of the 2020 ACM-SIAM Symposium on Discrete Algorithms, 2020
92020
Empirically measuring concentration: Fundamental limits on intrinsic robustness
S Mahloujifar, X Zhang, M Mahmoody, D Evans
arXiv preprint arXiv:1905.12202, 2019
92019
Adversarially robust learning could leverage computational hardness
S Garg, S Jha, S Mahloujifar, M Mahmoody
Proceedings of the 31st International Conference on Algorithmic Learning …, 2020
82020
Near linear-time community detection in networks with hardly detectable community structure
A Rezaei, SM Far, M Soleymani
2015 IEEE/ACM International Conference on Advances in Social Networks …, 2015
7*2015
Improving adversarial robustness using proxy distributions
V Sehwag, S Mahloujifar, T Handina, S Dai, C Xiang, M Chiang, P Mittal
arXiv preprint arXiv:2104.09425, 2021
32021
Model-Targeted Poisoning Attacks with Provable Convergence
F Suya, S Mahloujifar, A Suri, D Evans, Y Tian
arXiv preprint arXiv:2006.16469, 2020
32020
Property Inference From Poisoning
M Chase, E Ghosh, S Mahloujifar
arXiv preprint arXiv:2101.11073, 2021
22021
Learning under p-tampering poisoning attacks
S Mahloujifar, DI Diochnos, M Mahmoody
Annals of Mathematics and Artificial Intelligence 88 (7), 759-792, 2020
22020
Obliviousness Makes Poisoning Adversaries Weaker
S Garg, S Jha, S Mahloujifar, M Mahmoody, A Thakurta
arXiv preprint arXiv:2003.12020, 2020
22020
Lower Bounds for Adversarially Robust PAC Learning under Evasion and Hybrid Attacks
DI Diochnos, S Mahloujifar, M Mahmoody
2020 19th IEEE International Conference on Machine Learning and Applications …, 2020
2020
Model-Targeted Poisoning Attacks with Provable Convergence
F Suya, S Mahloujifar, D Evans, Y Tian
2020
Obliviousness Makes Poisoning Adversaries Weaker.
S Garg, S Jha, S Mahloujifar, M Mahmoody, A Thakurta
2020
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–20