Susmit Jha

verfied profile

∙

0 followers

∙

The University of Texas at San Antonio

∙

Intel

∙

United Technologies

∙

SRI International

Featured Co-authors

Somesh Jha
52 publications
Sanjit A. Seshia
52 publications
Abhinav Shrivastava
52 publications
Ananthram Swami
47 publications
Edgar Dobriban
23 publications
Karan Sikka
22 publications
Insup Lee
21 publications
Ajay Divakaran
20 publications
Chuchu Fan
17 publications
Shalini Ghosh
16 publications
Ashish Tiwari
15 publications

∙ 01/07/2022

iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection

Machine learning methods such as deep neural networks (DNNs), despite th...

Ramneet Kaur, et al. ∙

∙ 12/14/2021

Dual-Key Multimodal Backdoors for Visual Question Answering

The success of deep learning has enabled advances in multimodal tasks th...

Matthew Walmer, et al. ∙

∙ 09/09/2021

Protein Folding Neural Networks Are Not Robust

Deep neural networks such as AlphaFold and RoseTTAFold predict remarkabl...

Sumit Kumar Jha, et al. ∙

∙ 08/13/2021

Detecting OODs as datapoints with High Uncertainty

Deep neural networks (DNNs) are known to produce incorrect predictions w...

Ramneet Kaur, et al. ∙

∙ 03/29/2021

Online Defense of Trojaned Models using Misattributions

This paper proposes a new approach to detecting neural Trojans on Deep N...

Panagiota Kiourti, et al. ∙

∙ 03/23/2021

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

Deep neural networks (DNNs) are known to produce incorrect predictions w...

Ramneet Kaur, et al. ∙

∙ 12/03/2020

Detecting Trojaned DNNs Using Counterfactual Attributions

We target the problem of detecting Trojans or backdoors in DNNs. Such mo...

Karan Sikka, et al. ∙

∙ 11/25/2020

Learning Certified Control using Contraction Metric

In this paper, we solve the problem of finding a certified control polic...

Dawei Sun, et al. ∙

∙ 09/17/2020

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

Deep neural networks have been shown to be vulnerable to membership infe...

Sumit Kumar Jha, et al. ∙

∙ 10/29/2019

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

Given a Boolean formula ϕ(x) in conjunctive normal form (CNF), the densi...

Tuhin Sahai, et al. ∙

∙ 09/07/2019

On Need for Topology Awareness of Generative Models

Manifold assumption in learning states that: the data lie approximately ...

Uyeong Jang, et al. ∙

∙ 09/07/2019

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

ML algorithms or models, especially deep neural networks (DNNs), have sh...

Uyeong Jang, et al. ∙

∙ 03/14/2019

Attribution-driven Causal Analysis for Detection of Adversarial Examples

Attribution methods have been developed to explain the decision of a mac...

Susmit Jha, et al. ∙

∙ 03/01/2019

TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents

Recent work has identified that classification models implemented as neu...

Panagiota Kiourti, et al. ∙

∙ 05/18/2018

Trusted Neural Networks for Safety-Constrained Autonomous Control

We propose Trusted Neural Network (TNN) models, which are deep neural ne...

Shalini Ghosh, et al. ∙

∙ 10/11/2017

Specification Inference from Demonstrations

Learning from expert demonstrations has received a lot of attention in a...

Marcell Vazquez-Chanlatte, et al. ∙

∙ 09/26/2017

Output Range Analysis for Deep Neural Networks

Deep neural networks (NN) are extensively used for machine learning task...

Souradeep Dutta, et al. ∙

∙ 05/15/2015

A Theory of Formal Synthesis via Inductive Learning

Formal synthesis is the process of generating a program satisfying a hig...

Susmit Jha, et al. ∙

∙ 07/21/2014

Are There Good Mistakes? A Theoretical Analysis of CEGIS

Counterexample-guided inductive synthesis CEGIS is used to synthesize pr...

Susmit Jha, et al. ∙