activity
20182022
most citedMedKnowts: Unified Documentation and Information Retrieval for Electronic Health Records

22 citations · 41 across the 7 of their papers we have counts for

collaborators

13 papers

cs.CR2022

VPN: Verification of Poisoning in Neural Networks

Youcheng Sun, Muhammad Usman, Divya Gopinath +1

Neural networks are successfully used in a variety of applications, many of them having safety and security concerns. As a result researchers have proposed formal verification tech…

cs.CR2022

AntidoteRT: Run-time Detection and Correction of Poison Attacks on Neural Networks

Muhammad Usman, Youcheng Sun, Divya Gopinath +1

We study backdoor poisoning attacks against image classification networks, whereby an attacker inserts a trigger into a subset of the training data, in such a way that at test time…

cs.LG20213 cited

QuantifyML: How Good is my Machine Learning Model?

Muhammad Usman, Divya Gopinath, Corina S. Păsăreanu

The efficacy of machine learning models is typically determined by computing their accuracy on test data sets. However, this may often be misleading, since the test data may not be…

cs.HC202122 cited

MedKnowts: Unified Documentation and Information Retrieval for Electronic Health Records

Luke Murray, Divya Gopinath, Monica Agrawal +3

Clinical documentation can be transformed by Electronic Health Records, yet the documentation process is still a tedious, time-consuming, and error-prone process. Clinicians are fa…

cs.LG2021

NNrepair: Constraint-based Repair of Neural Network Classifiers

Muhammad Usman, Divya Gopinath, Youcheng Sun +2

We present NNrepair, a constraint-based technique for repairing neural network classifiers. The technique aims to fix the logic of the network at an intermediate layer or at the la…

cs.LG2021

NEUROSPF: A tool for the Symbolic Analysis of Neural Networks

Muhammad Usman, Yannic Noller, Corina Pasareanu +2

This paper presents NEUROSPF, a tool for the symbolic analysis of neural networks. Given a trained neural network model, the tool extracts the architecture and model parameters and…