Using Neural Architecture Search for Improving Software Flaw Detection in Multimodal Deep Learning Models

Technical Report · Tue Sep 01 00:00:00 EDT 2020

DOI:https://doi.org/10.2172/1668929· OSTI ID:1668929

Cooper, Alexis ^[1]; Zhou, Xin ^[2]; Dunlavy, Daniel ^[3]; Heidbrink, Scott ^[3]

---

1. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); North Carolina A & T State Univ., Greensboro, NC (United States)
2. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Univ. of Houston, TX (United States)
3. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

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.

• Research Organization: Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); North Carolina A & T State Univ., Greensboro, NC (United States); Univ. of Houston, TX (United States)
• Sponsoring Organization: USDOE National Nuclear Security Administration (NNSA)
• DOE Contract Number: AC04-94AL85000; NA0003525
• OSTI ID: 1668929
• Report Number(s): SAND--2020-9739; 690917
• Country of Publication: United States
• Language: English

Related Subjects

97 MATHEMATICS AND COMPUTING