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 Somesh Jha

Fairness Properties of Face Recognition and Obfuscation Systems


Aug 05, 2021
Harrison Rosenberg, Brian Tang, Kassem Fawaz, Somesh Jha


  Access Paper or Ask Questions

Domain Adaptation for Autoencoder-Based End-to-End Communication Over Wireless Channels


Aug 02, 2021
Jayaram Raghuram, Yijing Zeng, Dolores García Martí, Somesh Jha, Suman Banerjee, Joerg Widmer, Rafael Ruiz Ortiz

* Under Review. 22 pages, 8 figures 

  Access Paper or Ask Questions

Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles


Jun 29, 2021
Jiefeng Chen, Frederick Liu, Besim Avci, Xi Wu, Yingyu Liang, Somesh Jha


  Access Paper or Ask Questions

Towards Adversarial Robustness via Transductive Learning


Jun 15, 2021
Jiefeng Chen, Yang Guo, Xi Wu, Tianqi Li, Qicheng Lao, Yingyu Liang, Somesh Jha


  Access Paper or Ask Questions

A Shuffling Framework for Local Differential Privacy


Jun 11, 2021
Casey Meehan, Amrita Roy Chowdhury, Kamalika Chaudhuri, Somesh Jha


  Access Paper or Ask Questions

Causally Constrained Data Synthesis for Private Data Release


May 27, 2021
Varun Chandrasekaran, Darren Edge, Somesh Jha, Amit Sharma, Cheng Zhang, Shruti Tople


  Access Paper or Ask Questions

Hard-label Manifolds: Unexpected Advantages of Query Efficiency for Finding On-manifold Adversarial Examples


Mar 04, 2021
Washington Garcia, Pin-Yu Chen, Somesh Jha, Scott Clouse, Kevin R. B. Butler

* Preprint 

  Access Paper or Ask Questions

Exploring Adversarial Robustness of Deep Metric Learning


Feb 14, 2021
Thomas Kobber Panum, Zi Wang, Pengyu Kan, Earlence Fernandes, Somesh Jha


  Access Paper or Ask Questions

CaPC Learning: Confidential and Private Collaborative Learning


Feb 09, 2021
Christopher A. Choquette-Choo, Natalie Dullerud, Adam Dziedzic, Yunxiang Zhang, Somesh Jha, Nicolas Papernot, Xiao Wang

* Published as a conference paper at ICLR 2021 

  Access Paper or Ask Questions

Sample Complexity of Adversarially Robust Linear Classification on Separated Data


Dec 19, 2020
Robi Bhattacharjee, Somesh Jha, Kamalika Chaudhuri


  Access Paper or Ask Questions

ShadowNet: A Secure and Efficient System for On-device Model Inference


Nov 11, 2020
Zhichuang Sun, Ruimin Sun, Long Lu, Somesh Jha

* single column, 21 pages (30 pages include appendix), 7 figures 

  Access Paper or Ask Questions

An Attack on InstaHide: Is Private Learning Possible with Instance Encoding?


Nov 10, 2020
Nicholas Carlini, Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Shuang Song, Abhradeep Thakurta, Florian Tramer


  Access Paper or Ask Questions

Detecting Anomalous Inputs to DNN Classifiers By Joint Statistical Testing at the Layers


Jul 29, 2020
Jayaram Raghuram, Varun Chandrasekaran, Somesh Jha, Suman Banerjee

* 32 pages, 13 figures 

  Access Paper or Ask Questions

Abstract Universal Approximation for Neural Networks


Jul 14, 2020
Zi Wang, Aws Albarghouthi, Somesh Jha


  Access Paper or Ask Questions

Robust Learning against Logical Adversaries


Jul 01, 2020
Yizhen Wang, Xiaozhu Meng, Mihai Christodorescu, Somesh Jha


  Access Paper or Ask Questions

Robust Out-of-distribution Detection via Informative Outlier Mining


Jun 26, 2020
Jiefeng Chen, Yixuan Li, Xi Wu, Yingyu Liang, Somesh Jha


  Access Paper or Ask Questions

Continuous Release of Data Streams under both Centralized and Local Differential Privacy


May 24, 2020
Tianhao Wang, Joann Qiongna Chen, Zhikun Zhang, Dong Su, Yueqiang Cheng, Zhou Li, Ninghui Li, Somesh Jha


  Access Paper or Ask Questions

Representation Bayesian Risk Decompositions and Multi-Source Domain Adaptation


Apr 22, 2020
Xi Wu, Yang Guo, Jiefeng Chen, Yingyu Liang, Somesh Jha, Prasad Chalasani

* 25 pages, 6 figures 

  Access Paper or Ask Questions

Robust Out-of-distribution Detection for Neural Networks


Apr 05, 2020
Jiefeng Chen, Yixuan Li, Xi Wu, Yingyu Liang, Somesh Jha


  Access Paper or Ask Questions

Obliviousness Makes Poisoning Adversaries Weaker


Mar 26, 2020
Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Abhradeep Thakurta


  Access Paper or Ask Questions

Robust Out-of-distribution Detection in Neural Networks


Mar 24, 2020
Jiefeng Chen, Yixuan Li, Xi Wu, Yingyu Liang, Somesh Jha


  Access Paper or Ask Questions

Analyzing Accuracy Loss in Randomized Smoothing Defenses


Mar 03, 2020
Yue Gao, Harrison Rosenberg, Kassem Fawaz, Somesh Jha, Justin Hsu

* 19 pages, 6 figures, 2 tables 

  Access Paper or Ask Questions

CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods


Feb 18, 2020
Wei Zhang, Thomas Kobber Panum, Somesh Jha, Prasad Chalasani, David Page


  Access Paper or Ask Questions

Query-Efficient Physical Hard-Label Attacks on Deep Learning Visual Classification


Feb 17, 2020
Ryan Feng, Jiefeng Chen, Nelson Manohar, Earlence Fernandes, Somesh Jha, Atul Prakash


  Access Paper or Ask Questions

Semantic Robustness of Models of Source Code


Feb 07, 2020
Goutham Ramakrishnan, Jordan Henkel, Zi Wang, Aws Albarghouthi, Somesh Jha, Thomas Reps

* 19 pages 

  Access Paper or Ask Questions

On Need for Topology-Aware Generative Models for Manifold-Based Defenses


Oct 08, 2019
Uyeong Jang, Susmit Jha, Somesh Jha


  Access Paper or Ask Questions

Generating Semantic Adversarial Examples with Differentiable Rendering


Oct 02, 2019
Lakshya Jain, Wilson Wu, Steven Chen, Uyeong Jang, Varun Chandrasekaran, Sanjit Seshia, Somesh Jha


  Access Paper or Ask Questions

On Need for Topology Awareness of Generative Models


Sep 11, 2019
Uyeong Jang, Susmit Jha, Somesh Jha


  Access Paper or Ask Questions