Multimodal Deep Learning for Flaw Detection in Software Programs

09/09/2020 ∙ by Scott Heidbrink, et al. ∙ 0 ∙ share

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.

READ FULL TEXT

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

Software flaw detection using multimodal deep learning models has been d...
09/22/2020 ∙ by Alexis Cooper, et al. ∙ 11 ∙ share

read it
On the Feasibility of Transfer-learning Code Smells using Deep Learning

Context: A substantial amount of work has been done to detect smells in ...
04/05/2019 ∙ by Tushar Sharma, et al. ∙ 0 ∙ share

read it
The TrojAI Software Framework: An OpenSource tool for Embedding Trojans into Deep Learning Models

In this paper, we introduce the TrojAI software framework, an open sourc...
03/13/2020 ∙ by Kiran Karra, et al. ∙ 0 ∙ share

read it
Recent Trends in Deep Learning Based Personality Detection

In the recent times, automatic detection of human personality traits has...
08/07/2019 ∙ by Yash Mehta, et al. ∙ 8 ∙ share

read it
AST-Based Deep Learning for Detecting Malicious PowerShell

With the celebrated success of deep learning, some attempts to develop e...
10/03/2018 ∙ by Gili Rusak, et al. ∙ 0 ∙ share

read it
Live Trojan Attacks on Deep Neural Networks

Like all software systems, the execution of deep learning models is dict...
04/22/2020 ∙ by Robby Costales, et al. ∙ 5 ∙ share

read it
Building Program Vector Representations for Deep Learning

Deep learning has made significant breakthroughs in various fields of ar...
09/11/2014 ∙ by Lili Mou, et al. ∙ 0 ∙ share

read it

Multimodal Deep Learning for Flaw Detection in Software Programs

Authors

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

On the Feasibility of Transfer-learning Code Smells using Deep Learning

The TrojAI Software Framework: An OpenSource tool for Embedding Trojans into Deep Learning Models

Recent Trends in Deep Learning Based Personality Detection

AST-Based Deep Learning for Detecting Malicious PowerShell

Live Trojan Attacks on Deep Neural Networks

Building Program Vector Representations for Deep Learning

This week in AI