Susmit Jha

verfied profile

∙ 0 followers
Intel ∙ United Technologies ∙ SRI International

Detecting Trojaned DNNs Using Counterfactual Attributions

We target the problem of detecting Trojans or backdoors in DNNs. Such mo...
12/03/2020 ∙ by Karan Sikka, et al. ∙ 7 ∙ share

read it
Learning Certified Control using Contraction Metric

In this paper, we solve the problem of finding a certified control polic...
11/25/2020 ∙ by Dawei Sun, et al. ∙ 0 ∙ share

read it
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...
09/17/2020 ∙ by Sumit Kumar Jha, et al. ∙ 8 ∙ share

read it
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...
10/29/2019 ∙ by Tuhin Sahai, et al. ∙ 0 ∙ share

read it
On Need for Topology Awareness of Generative Models

Manifold assumption in learning states that: the data lie approximately ...
09/07/2019 ∙ by Uyeong Jang, et al. ∙ 20 ∙ share

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

ML algorithms or models, especially deep neural networks (DNNs), have sh...
09/07/2019 ∙ by Uyeong Jang, et al. ∙ 0 ∙ share

read it
Attribution-driven Causal Analysis for Detection of Adversarial Examples

Attribution methods have been developed to explain the decision of a mac...
03/14/2019 ∙ by Susmit Jha, et al. ∙ 6 ∙ share

read it
TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents

Recent work has identified that classification models implemented as neu...
03/01/2019 ∙ by Panagiota Kiourti, et al. ∙ 0 ∙ share

read it
Trusted Neural Networks for Safety-Constrained Autonomous Control

We propose Trusted Neural Network (TNN) models, which are deep neural ne...
05/18/2018 ∙ by Shalini Ghosh, et al. ∙ 0 ∙ share

read it
Specification Inference from Demonstrations

Learning from expert demonstrations has received a lot of attention in a...
10/11/2017 ∙ by Marcell Vazquez-Chanlatte, et al. ∙ 0 ∙ share

read it
Output Range Analysis for Deep Neural Networks

Deep neural networks (NN) are extensively used for machine learning task...
09/26/2017 ∙ by Souradeep Dutta, et al. ∙ 0 ∙ share

read it
A Theory of Formal Synthesis via Inductive Learning

Formal synthesis is the process of generating a program satisfying a hig...
05/15/2015 ∙ by Susmit Jha, et al. ∙ 0 ∙ share

read it
Are There Good Mistakes? A Theoretical Analysis of CEGIS

Counterexample-guided inductive synthesis CEGIS is used to synthesize pr...
07/21/2014 ∙ by Susmit Jha, et al. ∙ 0 ∙ share

read it

Susmit Jha

Featured Co-authors

Somesh Jha

Ananthram Swami

Sanjit A. Seshia

Karan Sikka

Ajay Divakaran

Shalini Ghosh

Ashish Tiwari

Wenchao Li

Chuchu Fan

Brian Jalaian

Alvaro Velasquez

Detecting Trojaned DNNs Using Counterfactual Attributions

Learning Certified Control using Contraction Metric

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

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

On Need for Topology Awareness of Generative Models

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

Attribution-driven Causal Analysis for Detection of Adversarial Examples

TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents

Trusted Neural Networks for Safety-Constrained Autonomous Control

Specification Inference from Demonstrations

Output Range Analysis for Deep Neural Networks

A Theory of Formal Synthesis via Inductive Learning

Are There Good Mistakes? A Theoretical Analysis of CEGIS