Software flaw detection using multimodal deep learning models has been demonstrated as a very competitive approach on benchmark problems. In this work, we demonstrate that even better performance can be achieved using neural architecture search (NAS) combined with multimodal learning models. We adapt a NAS framework aimed at investigating image classification to the problem of software flaw detection and demonstrate improved results on the Juliet Test Suite, a popular benchmarking data set for measuring performance of machine learning models in this problem domain.
@article{arxiv.2009.10644,
title = {Using Neural Architecture Search for Improving Software Flaw Detection in Multimodal Deep Learning Models},
author = {Alexis Cooper and Xin Zhou and Scott Heidbrink and Daniel M. Dunlavy},
journal= {arXiv preprint arXiv:2009.10644},
year = {2020}
}