Prateek Mittal

DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks

Feb 05, 2021
Chong Xiang, Prateek Mittal

A System for Efficiently Hunting for Cyber Threats in Computer Systems Using Threat Intelligence

Jan 17, 2021
Peng Gao, Fei Shao, Xiaoyuan Liu, Xusheng Xiao, Haoyuan Liu, Zheng Qin, Fengyuan Xu, Prateek Mittal, Sanjeev R. Kulkarni, Dawn Song

* Accepted paper at ICDE 2021 demonstrations track. arXiv admin note: substantial text overlap with arXiv:2010.13637

Access Paper or Ask Questions

* Presented at the ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning

Access Paper or Ask Questions

Time for a Background Check! Uncovering the impact of Background Features on Deep Neural Networks

Jun 24, 2020
Vikash Sehwag, Rajvardhan Oak, Mung Chiang, Prateek Mittal

* 6 pages, 5 figures

Access Paper or Ask Questions

PatchGuard: Provable Defense against Adversarial Patches Using Masks on Small Receptive Fields

Jun 08, 2020
Chong Xiang, Arjun Nitin Bhagoji, Vikash Sehwag, Prateek Mittal

Access Paper or Ask Questions

FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learning

Apr 05, 2020
Sameer Wagh, Shruti Tople, Fabrice Benhamouda, Eyal Kushilevitz, Prateek Mittal, Tal Rabin

Access Paper or Ask Questions

Systematic Evaluation of Privacy Risks of Machine Learning Models

Mar 24, 2020
Liwei Song, Prateek Mittal

* code is available at https://github.com/inspire-group/membership-inference-evaluation

Access Paper or Ask Questions

Towards Probabilistic Verification of Machine Unlearning

Mar 09, 2020
David Marco Sommer, Liwei Song, Sameer Wagh, Prateek Mittal

* code is available at https://github.com/inspire-group/unlearning-verification

Access Paper or Ask Questions

On Pruning Adversarially Robust Neural Networks

Feb 24, 2020
Vikash Sehwag, Shiqi Wang, Prateek Mittal, Suman Jana

* 19 pages, 14 figures, 8 tables

Access Paper or Ask Questions

Advances and Open Problems in Federated Learning

Dec 10, 2019
Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Keith Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D'Oliveira, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adrià Gascón, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaid Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konečný, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrède Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Özgür, Rasmus Pagh, Mariana Raykova, Hang Qi, Daniel Ramage, Ramesh Raskar, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao

Access Paper or Ask Questions

Lower Bounds on Adversarial Robustness from Optimal Transport

Oct 30, 2019
Arjun Nitin Bhagoji, Daniel Cullina, Prateek Mittal

* Accepted for the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019); 18 pages, 5 figures

Access Paper or Ask Questions

Towards Compact and Robust Deep Neural Networks

Jun 14, 2019
Vikash Sehwag, Shiqi Wang, Prateek Mittal, Suman Jana

* 14 pages, 9 figures, 7 tables

Access Paper or Ask Questions

Privacy Risks of Securing Machine Learning Models against Adversarial Examples

May 27, 2019
Liwei Song, Reza Shokri, Prateek Mittal

Access Paper or Ask Questions

Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples

May 05, 2019
Vikash Sehwag, Arjun Nitin Bhagoji, Liwei Song, Chawin Sitawarin, Daniel Cullina, Mung Chiang, Prateek Mittal

* 18 pages, 5 figures, 9 tables

Access Paper or Ask Questions

Robust Website Fingerprinting Through the Cache Occupancy Channel

Dec 11, 2018
Anatoly Shusterman, Lachlan Kang, Yarden Haskal, Yosef Meltser, Prateek Mittal, Yossi Oren, Yuval Yarom

Access Paper or Ask Questions

Analyzing Federated Learning through an Adversarial Lens

Nov 29, 2018
Arjun Nitin Bhagoji, Supriyo Chakraborty, Prateek Mittal, Seraphin Calo

* 18 pages, 12 figures

Access Paper or Ask Questions

Partial Recovery of Erdős-Rényi Graph Alignment via $k$-Core Alignment

Nov 03, 2018
Daniel Cullina, Negar Kiyavash, Prateek Mittal, H. Vincent Poor

Access Paper or Ask Questions

MVG Mechanism: Differential Privacy under Matrix-Valued Query

Oct 16, 2018
Thee Chanyaswad, Alex Dytso, H. Vincent Poor, Prateek Mittal

* Thee Chanyaswad, Alex Dytso, H. Vincent Poor, and Prateek Mittal. 2018. MVG Mechanism: Differential Privacy under Matrix-Valued Query. In 2018 ACM SIGSAC Conference on Computer and Communications Security (CCS'18)
* Appeared in CCS'18

Access Paper or Ask Questions

Prateek Mittal

DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks

A System for Efficiently Hunting for Cyber Threats in Computer Systems Using Threat Intelligence

Enabling Efficient Cyber Threat Hunting With Cyber Threat Intelligence

RobustBench: a standardized adversarial robustness benchmark

A Critical Evaluation of Open-World Machine Learning

Time for a Background Check! Uncovering the impact of Background Features on Deep Neural Networks

PatchGuard: Provable Defense against Adversarial Patches Using Masks on Small Receptive Fields

FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learning

Systematic Evaluation of Privacy Risks of Machine Learning Models

Towards Probabilistic Verification of Machine Unlearning

On Pruning Adversarially Robust Neural Networks

Advances and Open Problems in Federated Learning

Lower Bounds on Adversarial Robustness from Optimal Transport

Towards Compact and Robust Deep Neural Networks

Privacy Risks of Securing Machine Learning Models against Adversarial Examples

Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples

Robust Website Fingerprinting Through the Cache Occupancy Channel

Analyzing Federated Learning through an Adversarial Lens

Partial Recovery of Erdős-Rényi Graph Alignment via $k$-Core Alignment

MVG Mechanism: Differential Privacy under Matrix-Valued Query

PAC-learning in the presence of evasion adversaries

DARTS: Deceiving Autonomous Cars with Toxic Signs

Rogue Signs: Deceiving Traffic Sign Recognition with Malicious Ads and Logos

A Differential Privacy Mechanism Design Under Matrix-Valued Query

Enhancing Robustness of Machine Learning Systems via Data Transformations

On the Simultaneous Preservation of Privacy and Community Structure in Anonymized Networks