Följ
Arjun Bhagoji
Arjun Bhagoji
Andra namnArjun Nitin Bhagoji
Research Scientist, University of Chicago
Verifierad e-postadress på uchicago.edu - Startsida
Titel
Citeras av
Citeras av
År
Advances and open problems in federated learning
P Kairouz, HB McMahan, B Avent, A Bellet, M Bennis, AN Bhagoji, ...
Foundations and trends® in machine learning 14 (1–2), 1-210, 2021
51982021
Analyzing federated learning through an adversarial lens
AN Bhagoji, S Chakraborty, P Mittal, S Calo
International Conference on Machine Learning, 634-643, 2019
10612019
Enhancing Robustness of Machine Learning Systems via Data Transformations
AN Bhagoji, D Cullina, C Sitawarin, P Mittal
arXiv preprint arXiv:1704.02654, 2017
410*2017
Practical black-box attacks on deep neural networks using efficient query mechanisms
AN Bhagoji, W He, B Li, D Song
Proceedings of the European conference on computer vision (ECCV), 154-169, 2018
361*2018
Darts: Deceiving autonomous cars with toxic signs
C Sitawarin, AN Bhagoji, A Mosenia, M Chiang, P Mittal
arXiv preprint arXiv:1802.06430, 2018
2682018
Backdoor attacks on facial recognition in the physical world
E Wenger, J Passananti, AN Bhagoji, Y Yao, H Zheng, BY Zhao
arXiv preprint arXiv:2006.14580, 2020
169*2020
PAC-learning in the presence of evasion adversaries
D Cullina, AN Bhagoji, P Mittal
Advances in Neural Information Processing Systems, 228-239, 2018
142*2018
{PatchGuard}: A provably robust defense against adversarial patches via small receptive fields and masking
C Xiang, AN Bhagoji, V Sehwag, P Mittal
30th USENIX Security Symposium (USENIX Security 21), 2237-2254, 2021
1322021
Lower bounds on adversarial robustness from optimal transport
AN Bhagoji, D Cullina, P Mittal
Advances in Neural Information Processing Systems 32, 2019
942019
Analyzing the robustness of open-world machine learning
V Sehwag, AN Bhagoji, L Song, C Sitawarin, D Cullina, M Chiang, P Mittal
Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security …, 2019
93*2019
Rogue signs: Deceiving traffic sign recognition with malicious ads and logos
C Sitawarin, AN Bhagoji, A Mosenia, P Mittal, M Chiang
arXiv preprint arXiv:1801.02780, 2018
772018
Sparsefed: Mitigating model poisoning attacks in federated learning with sparsification
A Panda, S Mahloujifar, AN Bhagoji, S Chakraborty, P Mittal
International Conference on Artificial Intelligence and Statistics, 7587-7624, 2022
652022
Model poisoning attacks in federated learning
AN Bhagoji, S Chakraborty, P Mittal, S Calo
Proc. Workshop Secur. Mach. Learn.(SecML) 32nd Conf. Neural Inf. Process …, 2018
532018
Patch-based defenses against web fingerprinting attacks
S Shan, AN Bhagoji, H Zheng, BY Zhao
Proceedings of the 14th ACM Workshop on Artificial Intelligence and Security …, 2021
46*2021
Poison forensics: Traceback of data poisoning attacks in neural networks
S Shan, AN Bhagoji, H Zheng, BY Zhao
31st USENIX Security Symposium (USENIX Security 22), 3575-3592, 2022
37*2022
Advances and open problems in federated learning. arXiv
P Kairouz, HB McMahan, B Avent, A Bellet, M Bennis, AN Bhagoji, ...
arXiv preprint arXiv:1912.04977, 2019
302019
Finding Naturally Occurring Physical Backdoors in Image Datasets
E Wenger, R Bhattacharjee, AN Bhagoji, J Passananti, E Andere, ...
Thirty-sixth Conference on Neural Information Processing Systems Datasets …, 2022
15*2022
A critical evaluation of open-world machine learning
L Song, V Sehwag, AN Bhagoji, P Mittal
arXiv preprint arXiv:2007.04391, 2020
142020
Equivalence of 2D color codes (without translational symmetry) to surface codes
A Bhagoji, P Sarvepalli
2015 IEEE International Symposium on Information Theory (ISIT), 1109-1113, 2015
102015
Understanding robust learning through the lens of representation similarities
C Cianfarani, AN Bhagoji, V Sehwag, B Zhao, H Zheng, P Mittal
Advances in Neural Information Processing Systems 35, 34912-34925, 2022
92022
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–20