Publications
You can also find my articles on my Google Scholar profile.
Refereed Papers
2025
- Silencing Empowerment, Allowing Bigotry: Auditing the Moderation of Hate Speech on Twitch
with P. Shukla, W. Y. Chong, Y. Patel, B. Schaffner, D. Pruthi
63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025 - Adapting to Evolving Adversaries with Regularized Continual Robust Training
with S. Dai, C. Cianfarani, V. Sehwag, P. Mittal
42nd International Conference on Machine Learning (ICML), 2025
2024
- Feasibility of State Space Models for Network Traffic Generation
with A. Chu, X. Jiang, S. Liu, F. Bronzino, P. Schmitt, N. Feamster
SIGCOMM Workshop on Networks for AI Computing (NAIC) - Toward Automated DNS Tampering Detection Using Machine Learning
with P. Calle, L. Savitsky, N.P. Hoang, S. Cho
Free and Open Communications on the Internet (FOCI), 2024 - “Community Guidelines Make this the Best Party on the Internet”: An In-Depth Study of Online Platforms’ Content Moderation Policies
with B. Schaffner, S. Cheng, J. Mei, J. Shen, G. Wang, M. Chetty, N. Feamster, G. Lakier, C. Tan
ACM CHI Conference on Human Factors in Computing Systems, 2024
Website, Press - Towards Scalable and Robust Model Versioning
with W. Ding, B.Y. Zhao, H. Zheng
2nd IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 2024 - NetDiffusion: Network Data Augmentation Through Protocol-Constrained Traffic Generation
with X. Jiang, S. Liu, A. Gember-Jacobson, F. Bronzino, P. Schmitt, N. Feamster
Proceedings of the ACM on Measurement and Analysis of Computing Systems, 2024
2023
- Characterizing the Optimal 0-1 Loss for Multi-class Classification with a Test-time Attacker
with S. Dai, W. Ding, D. Cullina, B.Y. Zhao, H. Zheng, P. Mittal
36th Conference on Neural Information Processing Systems (NeurIPS), 2023 (Spotlight) - Lower Bounds on the Robustness of Fixed Feature Extractors to Test-time Adversaries
with D. Cullina and B. Y. Zhao
ICML 2023 Workshop on New Frontiers in Adversarial Machine Learning - LEAF: Navigating Concept Drift in Cellular Networks
with S. Liu, F. Bronzino, P. Schmitt, N. Feamster, H. G. Crespo, T. Coyle, B. Ward
Proceedings of the ACM on Networking, 2023 - Augmenting Rule-based DNS Censorship Detection at Scale with Machine Learning
with J.A.M. Brown, X. Jiang, V. Tran, N.P. Hoang, N. Feamster, P. Mittal, V. Yegneswaran
29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023
2022
- Finding Naturally Occurring Physical Backdoors in Image Datasets
with E. Wenger, R. Bhattacharjee, J. Passananti, E. Andere, H. Zheng and B. Y. Zhao
36th Conference on Neural Information Processing Systems (NeurIPS), 2022 - Understanding Robust Learning through the Lens of Representation Similarities
with C. Cianfarani, V. Sehwag, B. Y. Zhao and P. Mittal
36th Conference on Neural Information Processing Systems (NeurIPS), 2022 - Traceback of Data Poisoning Attacks in Neural Networks
with S. Shawn, H. Zheng and B. Y. Zhao
31st USENIX Security Symposium, 2022 - SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification
with A. Panda, S. Mahloujifar, S. Chakraborty and P. Mittal
25th International Conference on Artificial Intelligence and Statistics (AISTATS), 2022
2021
- A Real-time Defense against Website Fingerprinting Attacks
with S. Shawn, H. Zheng and B. Y. Zhao
14th ACM Workshop on Artificial Intelligence and Security (AISec), 2021 - PatchGuard: A Provable Robust Defense against Adversarial Patches via Small Receptive Fields and Masking
with C. Xiang, V. Sehwag and P. Mittal
30th USENIX Security Symposium (USENIX Security), 2021 - Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries
with D. Cullina, V. Sehwag and P. Mittal
38th International Conference on Machine Learning (ICML), 2021 - Backdoor Attacks on Facial Recognition in the Physical World
with E. Wenger, J. Passananti, Y. Yao, H. Zheng and B. Y. Zhao
Computer Vision and Pattern Recognition (CVPR), 2021
2019
- Lower Bounds on Adversarial Robustness from Optimal Transport
with D. Cullina and P. Mittal
33rd Conference on Neural Information Processing Systems (NeurIPS), 2019 - Analyzing the Robustness of Open-World Machine Learning
with V. Sehwag, L. Song, C. Sitawarin, D. Cullina, A. Mosenia, P. Mittal and M. Chiang
12th ACM Workshop on Artificial Intelligence and Security (AISec), 2019 - Analyzing Federated Learning through an Adversarial Lens
with S. Chakraborty, P. Mittal and S. Calo
36th International Conference on Machine Learning (ICML), 2019
2018
- PAC-learning in the presence of evasion adversaries
with D. Cullina and P. Mittal
32nd Conference on Neural Information Processing Systems (NeurIPS), 2018 - Rogue Signs: Deceiving Traffic Sign Recognition with Malicious Ads and Logos
with C. Sitawarin, A. Mosenia, M. Chiang and P. Mittal
1st Deep Learning and Security Workshop (co-located with IEEE S&P), 2018 - Practical Black-box Attacks on Deep Neural Networks using Efficient Query Mechanisms
with W. He, B. Li and D. Song
European Conference on Computer Vision (ECCV), 2018
2017 and earlier
- Enhancing robustness of machine learning systems via data transformations
with D. Cullina, C. Sitawarin and P. Mittal
52nd Annual Conference on Information Sciences and Systems (CISS), 2018 - Equivalence of 2D color codes (without translational symmetry) to surface codes
with P. Sarvepalli
International Symposium on Information Theory (ISIT), 2015
Pre-prints and papers under submission
- Adapting to Evolving Adversaries with Regularized Continual Robust Training
with S. Dai, C. Cianfarani, V. Sehwag and P. Mittal - MYCROFT: Towards Effective and Efficient External Data Augmentation
with Z. Sarwar, V. Tran,, N. Feamster, B. Y. Zhao and S. Chakraborty - Can Backdoor Attacks Survive Time-Varying Models?
with H. Li, H. Zheng and B. Y. Zhao
ArXiv 2022 - A Critical Evaluation of Open-world Machine Learning
with L. Song, V. Sehwag and P. Mittal
ArXiv 2020 - On the Local Equivalence of 2D Color Codes and Surface Codes with Applications
with A.B. Aloshious and P. Sarvepalli
ArXiv 2018
Books and Book Chapters
- Assessing vulnerabilities and securing federated learning
with S. Chakraborty
in Federated Learning: Theory and Practice - Adversarial Attacks for Anomaly Detection
with P. Shirani
in Springer Encyclopedia of Machine Learning and Data Science - Advances and Open Problems in Federated Learning
with P. Kairouz, H. B. McMahan et.al.
Foundations and Trends in Machine Learning (FnTML), 2021
Theses
- The Role of Data Geometry in Adversarial Machine Learning
Ph. D. Thesis, Department of Electrical and Computer Engineering, Princeton University, 2020 - Equivalence of color codes and surface codes
Dual Degree (B. Tech/M.Tech) Thesis, Department of Electrical Engineering, IIT Madras