Search Results for author: Matthew B. Dwyer

Found 7 papers, 5 papers with code

PCV: A Point Cloud-Based Network Verifier

no code implementations27 Jan 2023 Arup Kumar Sarker, Farzana Yasmin Ahmad, Matthew B. Dwyer

Due to complex architecture, dimension of hyper-parameter, and 3D convolution, no verifiers can perform the basic layer-wise verification.

White-box Testing of NLP models with Mask Neuron Coverage

no code implementations Findings (NAACL) 2022 Arshdeep Sekhon, Yangfeng Ji, Matthew B. Dwyer, Yanjun Qi

Recent literature has seen growing interest in using black-box strategies like CheckList for testing the behavior of NLP models.

Data Augmentation Fault Detection

Reducing DNN Properties to Enable Falsification with Adversarial Attacks

1 code implementation IEEE/ACM 43rd International Conference on Software Engineering (ICSE) 2021 David Shriver, Sebastian Elbaum, Matthew B. Dwyer

Deep Neural Networks (DNN) are increasingly being deployed in safety-critical domains, from autonomous vehicles to medical devices, where the consequences of errors demand techniques that can provide stronger guarantees about behavior than just high test accuracy.

Adversarial Attack Autonomous Vehicles

DNNV: A Framework for Deep Neural Network Verification

1 code implementation26 May 2021 David Shriver, Sebastian Elbaum, Matthew B. Dwyer

In this work we present DNNV, a framework for reducing the burden on DNN verifier researchers, developers, and users.

Distribution-Aware Testing of Neural Networks Using Generative Models

1 code implementation26 Feb 2021 Swaroopa Dola, Matthew B. Dwyer, Mary Lou Soffa

Using deep generative model based input validation, we show that all the three techniques generate significant number of invalid test inputs.

DNN Testing Test +1

Systematic Generation of Diverse Benchmarks for DNN Verification

1 code implementation14 Jul 2020 Dong Xu, David Shriver, Matthew B. Dwyer, Sebastian Elbaum

The field of verification has advanced due to the interplay of theoretical development and empirical evaluation.

Refactoring Neural Networks for Verification

2 code implementations6 Aug 2019 David Shriver, Dong Xu, Sebastian Elbaum, Matthew B. Dwyer

Deep neural networks (DNN) are growing in capability and applicability.

Cannot find the paper you are looking for? You can Submit a new open access paper.