
Detecting Trojaned DNNs Using Counterfactual Attributions
We target the problem of detecting Trojans or backdoors in DNNs. Such mo...
read it

Learning Certified Control using Contraction Metric
In this paper, we solve the problem of finding a certified control polic...
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...
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...
read it

On Need for Topology Awareness of Generative Models
Manifold assumption in learning states that: the data lie approximately ...
read it

On Need for TopologyAware Generative Models for ManifoldBased Defenses
ML algorithms or models, especially deep neural networks (DNNs), have sh...
read it

Attributiondriven Causal Analysis for Detection of Adversarial Examples
Attribution methods have been developed to explain the decision of a mac...
read it

TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents
Recent work has identified that classification models implemented as neu...
read it

Trusted Neural Networks for SafetyConstrained Autonomous Control
We propose Trusted Neural Network (TNN) models, which are deep neural ne...
read it

Specification Inference from Demonstrations
Learning from expert demonstrations has received a lot of attention in a...
read it

Output Range Analysis for Deep Neural Networks
Deep neural networks (NN) are extensively used for machine learning task...
read it

A Theory of Formal Synthesis via Inductive Learning
Formal synthesis is the process of generating a program satisfying a hig...
read it

Are There Good Mistakes? A Theoretical Analysis of CEGIS
Counterexampleguided inductive synthesis CEGIS is used to synthesize pr...
read it
Susmit Jha
verfied profile