Machine Learning Techniques for Python Source Code Vulnerability Detection

Software vulnerabilities are a fundamental reason for the prevalence of cyber attacks and their identification is a crucial yet challenging problem in cyber security. In this paper, we apply and compare different machine learning algorithms for source code vulnerability detection specifically for Py...

Full description

Saved in:
Bibliographic Details
Main Authors Farasat, Talaya, Posegga, Joachim
Format Journal Article
LanguageEnglish
Published 15.04.2024
Subjects
Computer Science - Artificial Intelligence
Computer Science - Software Engineering
Online AccessGet full text
DOI10.48550/arxiv.2404.09537

Cover

More Information
Summary:Software vulnerabilities are a fundamental reason for the prevalence of cyber attacks and their identification is a crucial yet challenging problem in cyber security. In this paper, we apply and compare different machine learning algorithms for source code vulnerability detection specifically for Python programming language. Our experimental evaluation demonstrates that our Bidirectional Long Short-Term Memory (BiLSTM) model achieves a remarkable performance (average Accuracy = 98.6%, average F-Score = 94.7%, average Precision = 96.2%, average Recall = 93.3%, average ROC = 99.3%), thereby, establishing a new benchmark for vulnerability detection in Python source code.
DOI:10.48550/arxiv.2404.09537