Multimodal Deep Learning for Flaw Detection in Software Programs

TL;DR

This paper demonstrates that combining multiple representations of software programs through multimodal deep learning significantly improves flaw detection accuracy compared to using single representations.

Contribution

It introduces a novel application of multimodal deep learning models to software flaw detection, outperforming traditional single-representation methods.

Findings

Multimodal models outperform single-representation models in flaw detection.

The approach improves detection accuracy on Juliet Test Suite and Linux Kernel.

Adapts three multimodal deep learning models for software flaw detection.

Abstract

We explore the use of multiple deep learning models for detecting flaws in software programs. Current, standard approaches for flaw detection rely on a single representation of a software program (e.g., source code or a program binary). We illustrate that, by using techniques from multimodal deep learning, we can simultaneously leverage multiple representations of software programs to improve flaw detection over single representation analyses. Specifically, we adapt three deep learning models from the multimodal learning literature for use in flaw detection and demonstrate how these models outperform traditional deep learning models. We present results on detecting software flaws using the Juliet Test Suite and Linux Kernel.