Loading…
Software Vulnerability Detection Based on Binary Intermediate Slicing
Software vulnerability is one of the root causes of network security attacks. Attackers use software vulnerabilities to launch network attacks, which poses a great challenge to the development of information systems and artificial intelligence. Timely detection of security issues in software is cruc...
Saved in:
Main Authors: | , , |
---|---|
Format: | Conference Proceeding |
Language: | English |
Subjects: | |
Online Access: | Request full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | Software vulnerability is one of the root causes of network security attacks. Attackers use software vulnerabilities to launch network attacks, which poses a great challenge to the development of information systems and artificial intelligence. Timely detection of security issues in software is crucial to reduce security risks. Based on the research on binary program vulnerability detection, aiming at the problems of high false positive rate, relying on expert experience and coarse measurement granularity in the existing binary vulnerability detection technology, this paper proposes an intelligent binary code vulnerability detection approach based on program slicing and deep learning. It first extracts program slices and converts them into vectors. After that, a deep learning model is trained and constructed with the vectors. We conduct experiments on three datasets from SARD (Software Assurance Reference Dataset) and the results show our approach could achieve good vulnerability detection effectiveness. |
---|---|
ISSN: | 2693-9371 |
DOI: | 10.1109/QRS-C60940.2023.00087 |