Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Prateek Mittal

Prateek Mittal

SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification


Dec 12, 2021
Ashwinee Panda, Saeed Mahloujifar, Arjun N. Bhagoji, Supriyo Chakraborty, Prateek Mittal

Figure 1 for SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification
Figure 2 for SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification
Figure 3 for SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification
Figure 4 for SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification

  Access Paper or Ask Questions

Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture


Oct 15, 2021
Xinyu Tang, Saeed Mahloujifar, Liwei Song, Virat Shejwalkar, Milad Nasr, Amir Houmansadr, Prateek Mittal

Figure 1 for Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture
Figure 2 for Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture
Figure 3 for Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture
Figure 4 for Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture

  Access Paper or Ask Questions

Parameterizing Activation Functions for Adversarial Robustness


Oct 11, 2021
Sihui Dai, Saeed Mahloujifar, Prateek Mittal

Figure 1 for Parameterizing Activation Functions for Adversarial Robustness
Figure 2 for Parameterizing Activation Functions for Adversarial Robustness
Figure 3 for Parameterizing Activation Functions for Adversarial Robustness
Figure 4 for Parameterizing Activation Functions for Adversarial Robustness

  Access Paper or Ask Questions

PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier


Aug 20, 2021
Chong Xiang, Saeed Mahloujifar, Prateek Mittal

Figure 1 for PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier
Figure 2 for PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier
Figure 3 for PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier
Figure 4 for PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier

  Access Paper or Ask Questions

PatchGuard++: Efficient Provable Attack Detection against Adversarial Patches


Apr 26, 2021
Chong Xiang, Prateek Mittal

Figure 1 for PatchGuard++: Efficient Provable Attack Detection against Adversarial Patches
* ICLR 2021 Workshop on Security and Safety in Machine Learning Systems 
  Access Paper or Ask Questions

Improving Adversarial Robustness Using Proxy Distributions


Apr 19, 2021
Vikash Sehwag, Saeed Mahloujifar, Tinashe Handina, Sihui Dai, Chong Xiang, Mung Chiang, Prateek Mittal

Figure 1 for Improving Adversarial Robustness Using Proxy Distributions
Figure 2 for Improving Adversarial Robustness Using Proxy Distributions
Figure 3 for Improving Adversarial Robustness Using Proxy Distributions
Figure 4 for Improving Adversarial Robustness Using Proxy Distributions
* 24 pages, 5 figures, 4 tables 
  Access Paper or Ask Questions

Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries


Apr 16, 2021
Arjun Nitin Bhagoji, Daniel Cullina, Vikash Sehwag, Prateek Mittal

Figure 1 for Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries
Figure 2 for Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries
Figure 3 for Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries
Figure 4 for Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries
* 16 pages, 12 figures; Under review 
  Access Paper or Ask Questions

SSD: A Unified Framework for Self-Supervised Outlier Detection


Mar 22, 2021
Vikash Sehwag, Mung Chiang, Prateek Mittal

Figure 1 for SSD: A Unified Framework for Self-Supervised Outlier Detection
Figure 2 for SSD: A Unified Framework for Self-Supervised Outlier Detection
Figure 3 for SSD: A Unified Framework for Self-Supervised Outlier Detection
Figure 4 for SSD: A Unified Framework for Self-Supervised Outlier Detection
* ICLR 2021 
  Access Paper or Ask Questions

DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks


Feb 05, 2021
Chong Xiang, Prateek Mittal

Figure 1 for DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks
Figure 2 for DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks
Figure 3 for DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks
Figure 4 for DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks

  Access Paper or Ask Questions

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

Figure 1 for A System for Efficiently Hunting for Cyber Threats in Computer Systems Using Threat Intelligence
Figure 2 for A System for Efficiently Hunting for Cyber Threats in Computer Systems Using Threat Intelligence
Figure 3 for A System for Efficiently Hunting for Cyber Threats in Computer Systems Using Threat Intelligence
* Accepted paper at ICDE 2021 demonstrations track. arXiv admin note: substantial text overlap with arXiv:2010.13637 
  Access Paper or Ask Questions

Enabling Efficient Cyber Threat Hunting With Cyber Threat Intelligence


Oct 26, 2020
Peng Gao, Fei Shao, Xiaoyuan Liu, Xusheng Xiao, Zheng Qin, Fengyuan Xu, Prateek Mittal, Sanjeev R. Kulkarni, Dawn Song

Figure 1 for Enabling Efficient Cyber Threat Hunting With Cyber Threat Intelligence
Figure 2 for Enabling Efficient Cyber Threat Hunting With Cyber Threat Intelligence
Figure 3 for Enabling Efficient Cyber Threat Hunting With Cyber Threat Intelligence
Figure 4 for Enabling Efficient Cyber Threat Hunting With Cyber Threat Intelligence

  Access Paper or Ask Questions

RobustBench: a standardized adversarial robustness benchmark


Oct 19, 2020
Francesco Croce, Maksym Andriushchenko, Vikash Sehwag, Nicolas Flammarion, Mung Chiang, Prateek Mittal, Matthias Hein

Figure 1 for RobustBench: a standardized adversarial robustness benchmark
Figure 2 for RobustBench: a standardized adversarial robustness benchmark
Figure 3 for RobustBench: a standardized adversarial robustness benchmark
Figure 4 for RobustBench: a standardized adversarial robustness benchmark

  Access Paper or Ask Questions

A Critical Evaluation of Open-World Machine Learning


Jul 08, 2020
Liwei Song, Vikash Sehwag, Arjun Nitin Bhagoji, Prateek Mittal

Figure 1 for A Critical Evaluation of Open-World Machine Learning
Figure 2 for A Critical Evaluation of Open-World Machine Learning
Figure 3 for A Critical Evaluation of Open-World Machine Learning
Figure 4 for A Critical Evaluation of Open-World Machine Learning
* 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

Figure 1 for Time for a Background Check! Uncovering the impact of Background Features on Deep Neural Networks
Figure 2 for Time for a Background Check! Uncovering the impact of Background Features on Deep Neural Networks
Figure 3 for Time for a Background Check! Uncovering the impact of Background Features on Deep Neural Networks
Figure 4 for Time for a Background Check! Uncovering the impact of Background Features on Deep Neural Networks
* 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

Figure 1 for PatchGuard: Provable Defense against Adversarial Patches Using Masks on Small Receptive Fields
Figure 2 for PatchGuard: Provable Defense against Adversarial Patches Using Masks on Small Receptive Fields
Figure 3 for PatchGuard: Provable Defense against Adversarial Patches Using Masks on Small Receptive Fields
Figure 4 for PatchGuard: Provable Defense against Adversarial Patches Using Masks on Small Receptive Fields

  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

Figure 1 for FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learning
Figure 2 for FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learning
Figure 3 for FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learning
Figure 4 for FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learning

  Access Paper or Ask Questions

Systematic Evaluation of Privacy Risks of Machine Learning Models


Mar 24, 2020
Liwei Song, Prateek Mittal

Figure 1 for Systematic Evaluation of Privacy Risks of Machine Learning Models
Figure 2 for Systematic Evaluation of Privacy Risks of Machine Learning Models
Figure 3 for Systematic Evaluation of Privacy Risks of Machine Learning Models
Figure 4 for Systematic Evaluation of Privacy Risks of Machine Learning Models
* 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

Figure 1 for Towards Probabilistic Verification of Machine Unlearning
Figure 2 for Towards Probabilistic Verification of Machine Unlearning
Figure 3 for Towards Probabilistic Verification of Machine Unlearning
Figure 4 for Towards Probabilistic Verification of Machine Unlearning
* 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

Figure 1 for On Pruning Adversarially Robust Neural Networks
Figure 2 for On Pruning Adversarially Robust Neural Networks
Figure 3 for On Pruning Adversarially Robust Neural Networks
Figure 4 for On Pruning Adversarially Robust Neural Networks
* 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

Figure 1 for Advances and Open Problems in Federated Learning
Figure 2 for Advances and Open Problems in Federated Learning
Figure 3 for Advances and Open Problems in Federated Learning
Figure 4 for Advances and Open Problems in Federated Learning

  Access Paper or Ask Questions

Lower Bounds on Adversarial Robustness from Optimal Transport


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

Figure 1 for Lower Bounds on Adversarial Robustness from Optimal Transport
Figure 2 for Lower Bounds on Adversarial Robustness from Optimal Transport
Figure 3 for Lower Bounds on Adversarial Robustness from Optimal Transport
Figure 4 for Lower Bounds on Adversarial Robustness from Optimal Transport
* 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

Figure 1 for Towards Compact and Robust Deep Neural Networks
Figure 2 for Towards Compact and Robust Deep Neural Networks
Figure 3 for Towards Compact and Robust Deep Neural Networks
Figure 4 for Towards Compact and Robust Deep Neural Networks
* 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

Figure 1 for Privacy Risks of Securing Machine Learning Models against Adversarial Examples
Figure 2 for Privacy Risks of Securing Machine Learning Models against Adversarial Examples
Figure 3 for Privacy Risks of Securing Machine Learning Models against Adversarial Examples
Figure 4 for Privacy Risks of Securing Machine Learning Models against Adversarial Examples

  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

Figure 1 for Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples
Figure 2 for Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples
Figure 3 for Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples
Figure 4 for Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples
* 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

Figure 1 for Robust Website Fingerprinting Through the Cache Occupancy Channel
Figure 2 for Robust Website Fingerprinting Through the Cache Occupancy Channel
Figure 3 for Robust Website Fingerprinting Through the Cache Occupancy Channel
Figure 4 for Robust Website Fingerprinting Through the Cache Occupancy Channel

  Access Paper or Ask Questions

Analyzing Federated Learning through an Adversarial Lens


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

Figure 1 for Analyzing Federated Learning through an Adversarial Lens
Figure 2 for Analyzing Federated Learning through an Adversarial Lens
Figure 3 for Analyzing Federated Learning through an Adversarial Lens
Figure 4 for Analyzing Federated Learning through an Adversarial Lens
* 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

Figure 1 for Partial Recovery of Erdős-Rényi Graph Alignment via $k$-Core Alignment
Figure 2 for Partial Recovery of Erdős-Rényi Graph Alignment via $k$-Core Alignment

  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

Figure 1 for MVG Mechanism: Differential Privacy under Matrix-Valued Query
Figure 2 for MVG Mechanism: Differential Privacy under Matrix-Valued Query
Figure 3 for MVG Mechanism: Differential Privacy under Matrix-Valued Query
Figure 4 for MVG Mechanism: Differential Privacy under Matrix-Valued Query
* 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