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 Susmit Jha

Susmit Jha

Strategic CAD Labs, Intel

Online Defense of Trojaned Models using Misattributions


Mar 29, 2021
Panagiota Kiourti, Wenchao Li, Anirban Roy, Karan Sikka, Susmit Jha


  Access Paper or Ask Questions

Are all outliers alike? On Understanding the Diversity of Outliers for Detecting OODs


Mar 23, 2021
Ramneet Kaur, Susmit Jha, Anirban Roy, Oleg Sokolsky, Insup Lee


  Access Paper or Ask Questions

Detecting Trojaned DNNs Using Counterfactual Attributions


Dec 03, 2020
Karan Sikka, Indranil Sur, Susmit Jha, Anirban Roy, Ajay Divakaran


  Access Paper or Ask Questions

Learning Certified Control using Contraction Metric


Nov 25, 2020
Dawei Sun, Susmit Jha, Chuchu Fan

* Accepted to Conference on Robot Learning (CoRL) 2020 

  Access Paper or Ask Questions

An Extension of Fano's Inequality for Characterizing Model Susceptibility to Membership Inference Attacks


Sep 17, 2020
Sumit Kumar Jha, Susmit Jha, Rickard Ewetz, Sunny Raj, Alvaro Velasquez, Laura L. Pullum, Ananthram Swami

* 9 pages, 3 figures 

  Access Paper or Ask Questions

Estimating the Density of States of Boolean Satisfiability Problems on Classical and Quantum Computing Platforms


Oct 29, 2019
Tuhin Sahai, Anurag Mishra, Jose Miguel Pasini, Susmit Jha


  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

On Need for Topology Awareness of Generative Models


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


  Access Paper or Ask Questions

Attribution-driven Causal Analysis for Detection of Adversarial Examples


Mar 14, 2019
Susmit Jha, Sunny Raj, Steven Lawrence Fernandes, Sumit Kumar Jha, Somesh Jha, Gunjan Verma, Brian Jalaian, Ananthram Swami

* 11 pages, 6 figures 

  Access Paper or Ask Questions

TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents


Mar 01, 2019
Panagiota Kiourti, Kacper Wardega, Susmit Jha, Wenchao Li


  Access Paper or Ask Questions

Learning Task Specifications from Demonstrations


Oct 27, 2018
Marcell Vazquez-Chanlatte, Susmit Jha, Ashish Tiwari, Mark K. Ho, Sanjit A. Seshia

* NIPS 2018 

  Access Paper or Ask Questions

Trusted Neural Networks for Safety-Constrained Autonomous Control


May 18, 2018
Shalini Ghosh, Amaury Mercier, Dheeraj Pichapati, Susmit Jha, Vinod Yegneswaran, Patrick Lincoln


  Access Paper or Ask Questions

Output Range Analysis for Deep Neural Networks


Sep 26, 2017
Souradeep Dutta, Susmit Jha, Sriram Sanakaranarayanan, Ashish Tiwari


  Access Paper or Ask Questions

A Theory of Formal Synthesis via Inductive Learning


May 21, 2016
Susmit Jha, Sanjit A. Seshia


  Access Paper or Ask Questions

Are There Good Mistakes? A Theoretical Analysis of CEGIS


Jul 21, 2014
Susmit Jha, Sanjit A. Seshia

* EPTCS 157, 2014, pp. 84-99 
* In Proceedings SYNT 2014, arXiv:1407.4937 

  Access Paper or Ask Questions

Statistical Analysis of Privacy and Anonymity Guarantees in Randomized Security Protocol Implementations


Jun 27, 2009
Susmit Jha


  Access Paper or Ask Questions