Sotabase

Career

· Assistant Professor, Indian Institute of Technology, Bombay2025–
· Research Scientist, University of Chicago2023–2025
· Postdoctoral Scholar, University of Chicago2020–2023
· Research Intern, IBM2018–2018
· Visiting Researcher, University of California, Berkeley2017–2017
· Doctor of Philosophy (Ph.D.), Princeton University2015–2020
· Graduate Research Assistant, Princeton University2015–2020
· Master’s Degree, Indian Institute of Technology, Madras2014–2015
· Summer Intern, Reliance IITM Telecom Centre of Excellence2012–2012
· Bachelor’s Degree, Indian Institute of Technology, Madras2010–2014

Publications (47)

Advances and Open Problems in Federated Learning
Found. Trends Mach. Learn. · 2019
7,730
cited
Analyzing Federated Learning through an Adversarial Lens
International Conference on Machine Learning · 2018
1,237
cited
Practical Black-Box Attacks on Deep Neural Networks Using Efficient Query Mechanisms
European Conference on Computer Vision · 2018
276
cited
DARTS: Deceiving Autonomous Cars with Toxic Signs
arXiv.org · 2018
246
cited
Enhancing robustness of machine learning systems via data transformations
Annual Conference on Information Sciences and Systems · 2017
243
cited
Backdoor Attacks Against Deep Learning Systems in the Physical World
Computer Vision and Pattern Recognition · 2020
241
cited
PatchGuard: A Provably Robust Defense against Adversarial Patches via Small Receptive Fields and Masking
USENIX Security Symposium · 2020
166
cited
Dimensionality Reduction as a Defense against Evasion Attacks on Machine Learning Classifiers
arXiv.org · 2017
161
cited
SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification
International Conference on Artificial Intelligence and Statistics · 2021
117
cited
PAC-learning in the presence of adversaries
Neural Information Processing Systems · 2018
103
cited
Lower Bounds on Adversarial Robustness from Optimal Transport
Neural Information Processing Systems · 2019
97
cited
Analyzing the Robustness of Open-World Machine Learning
AISec@CCS · 2019
80
cited
NetDiffusion: Network Data Augmentation Through Protocol-Constrained Traffic Generation
Proceedings of the ACM on Measurement and Analysis of Computing Systems · 2023
72
cited
Rogue Signs: Deceiving Traffic Sign Recognition with Malicious Ads and Logos
arXiv.org · 2018
70
cited
Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks
USENIX Security Symposium · 2021
63
cited
PAC-learning in the presence of evasion adversaries
Neural Information Processing Systems · 2018
56
cited
Patch-based Defenses against Web Fingerprinting Attacks
AISec@CCS · 2021
34
cited
PatchGuard: Provable Defense against Adversarial Patches Using Masks on Small Receptive Fields
arXiv.org · 2020
29
cited
Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples
arXiv.org · 2019
26
cited
"Community Guidelines Make this the Best Party on the Internet": An In-Depth Study of Online Platforms' Content Moderation Policies
International Conference on Human Factors in Computing Systems · 2024
26
cited
Sotabase
Arjun Nitin Bhagoji | Researcher Profile | Sotabase | Sotabase