Software Vulnerability Detection Using Deep Neural Networks: A Survey

The constantly increasing number of disclosed security vulnerabilities have become an important concern in the software industry and in the field of cybersecurity, suggesting that the current approaches for vulnerability detection demand further improvement. The booming of the open-source software c...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the IEEE 2020-10, Vol.108 (10), p.1825-1848
Main Authors: Lin, Guanjun, Wen, Sheng, Han, Qing-Long, Zhang, Jun, Xiang, Yang
Format: Article
Language:English
Subjects:
Artificial neural networks
Computer bugs
Computer security
Cybersecurity
Data mining
Deep learning
deep neural network (DNN)
Feature extraction
Literature reviews
Machine learning
machine learning (ML)
Machine translation
Neural networks
Open source software
representation learning
Semantics
Software engineering
Software reliability
software vulnerability
Source code
Speech recognition
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The constantly increasing number of disclosed security vulnerabilities have become an important concern in the software industry and in the field of cybersecurity, suggesting that the current approaches for vulnerability detection demand further improvement. The booming of the open-source software community has made vast amounts of software code available, which allows machine learning and data mining techniques to exploit abundant patterns within software code. Particularly, the recent breakthrough application of deep learning to speech recognition and machine translation has demonstrated the great potential of neural models' capability of understanding natural languages. This has motivated researchers in the software engineering and cybersecurity communities to apply deep learning for learning and understanding vulnerable code patterns and semantics indicative of the characteristics of vulnerable code. In this survey, we review the current literature adopting deep-learning-/neural-network-based approaches for detecting software vulnerabilities, aiming at investigating how the state-of-the-art research leverages neural techniques for learning and understanding code semantics to facilitate vulnerability discovery. We also identify the challenges in this new field and share our views of potential research directions.
ISSN:0018-9219
1558-2256
DOI:10.1109/JPROC.2020.2993293