Somesh Jha

Professor

Department of Computer Sciences, University of Wisconsin, Madison

Show Academic Trajectory

Ego Network

D-Core

Research Interests

Author Statistics

ACM_Citations

USA-2016
For contributions to verification, programming languages, and software engineering. Press Release
USA-2014

Experience

Education

Bio

My main areas of interests are at the intersection of security and formal methods (FM). Currently my active interests are in adversarial machine learning (AML) and privacy.

Papers383 papers

Sort

By YearBy Citation

Robust Out-of-distribution Detection via Informative Outlier Mining

Jiefeng Chen, Yixuan Li,Xi Wu,Yingyu Liang,Somesh Jha

Bibtex

Exploring Connections Between Active Learning and Model Extraction

Varun Chandrasekaran,Kamalika Chaudhuri,Irene Giacomelli,Somesh Jha,Songbai Yan

USENIX Security Symposium, pp.1309-1326, (2020)

EIBibtex

Sample Complexity of Adversarially Robust Linear Classification on Separated Data

Robi Bhattacharjee,Somesh Jha,Kamalika Chaudhuri

Bibtex

CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods

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

Proceedings of the ... International Conference on Machine Learning. International Conference on Mac..., (2020): 11235-11245

WOSBibtex

Data-Dependent Differentially Private Parameter Learning for Directed Graphical Models

Amrita Roy Chowdhury,Theodoros Rekatsinas,Somesh Jha

ICML, pp.1939-1951, (2020)

EIBibtex

Overfitting, robustness, and malicious algorithms: A study of potential causes of privacy risk in machine learning

Samuel Yeom, Irene Giacomelli, Alan Menaged,Matt Fredrikson,Somesh Jha

Journal of Computer Security, no. 1 (2020): 35-70

Cited by1EIBibtex

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

Uyeong Jang,Susmit Jha,Somesh Jha

ICLR, (2020)

EIBibtex

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

Zhichuang Sun, Ruimin Sun,Long Lu,Somesh Jha

Bibtex

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

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

Bibtex

Semantic Adversarial Deep Learning

Sanjit A. Seshia,Somesh Jha, Tommaso Dreossi

IEEE Design & Test of Computers, pp.1-1, (2020)

Bibtex

Semantic Robustness of Models of Source Code

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

Bibtex

CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods

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

ICML, pp.11235-11245, (2020)

Cited by2EIBibtex

Obliviousness Makes Poisoning Adversaries Weaker

Garg Sanjam,Jha Somesh, Mahloujifar Saeed,Mahmoody Mohammad, Thakurta Abhradeep

Bibtex

Towards Effective Differential Privacy Communication for Users' Data Sharing Decision and Comprehension

Xiong Aiping, Wang Tianhao,Li Ninghui,Jha Somesh

IEEE Symposium on Security and Privacy, pp.392-410, (2020)

EIBibtex

Semantic Adversarial Deep Learning

Sanjit A. Seshia,Somesh Jha,Tommaso Dreossi

IEEE Design & Test, no. 2 (2020): 8-18

EIWOSBibtex

Intertwining Order Preserving Encryption and Differential Privacy

Amrita Roy Chowdhury,Bolin Ding,Somesh Jha, Weiran Liu,Jingren Zhou

Bibtex

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

Jayaram Raghuram,Varun Chandrasekaran,Somesh Jha, Suman Banerjee

Bibtex

Representation Bayesian Risk Decompositions and Multi-Source Domain Adaptation

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

Cited by1Bibtex

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

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

Bibtex

Crypt?: Crypto-Assisted Differential Privacy on Untrusted Servers

Amrita Roy Chowdhury, Chenghong Wang, Xi He,Ashwin Machanavajjhala,Somesh Jha

SIGMOD/PODS '20: International Conference on Management of Data Portland OR ..., pp.603-619, (2020)

EIBibtex

View All

Base Info Papers Patents Projects