EnStack: An Ensemble Stacking Framework of Large Language Models for Enhanced Vulnerability Detection in Source Code

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ridoy, Shahriyar Zaman, Shaon, Md. Shazzad Hossain, Cuzzocrea, Alfredo, Akter, Mst Shapna
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917847858413568
author Ridoy, Shahriyar Zaman
Shaon, Md. Shazzad Hossain
Cuzzocrea, Alfredo
Akter, Mst Shapna
author_facet Ridoy, Shahriyar Zaman
Shaon, Md. Shazzad Hossain
Cuzzocrea, Alfredo
Akter, Mst Shapna
contents Automated detection of software vulnerabilities is critical for enhancing security, yet existing methods often struggle with the complexity and diversity of modern codebases. In this paper, we introduce EnStack, a novel ensemble stacking framework that enhances vulnerability detection using natural language processing (NLP) techniques. Our approach synergizes multiple pre-trained large language models (LLMs) specialized in code understanding CodeBERT for semantic analysis, GraphCodeBERT for structural representation, and UniXcoder for cross-modal capabilities. By fine-tuning these models on the Draper VDISC dataset and integrating their outputs through meta-classifiers such as Logistic Regression, Support Vector Machines (SVM), Random Forest, and XGBoost, EnStack effectively captures intricate code patterns and vulnerabilities that individual models may overlook. The meta-classifiers consolidate the strengths of each LLM, resulting in a comprehensive model that excels in detecting subtle and complex vulnerabilities across diverse programming contexts. Experimental results demonstrate that EnStack significantly outperforms existing methods, achieving notable improvements in accuracy, precision, recall, and F1-score. This work highlights the potential of ensemble LLM approaches in code analysis tasks and offers valuable insights into applying NLP techniques for advancing automated vulnerability detection.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16561
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EnStack: An Ensemble Stacking Framework of Large Language Models for Enhanced Vulnerability Detection in Source Code
Ridoy, Shahriyar Zaman
Shaon, Md. Shazzad Hossain
Cuzzocrea, Alfredo
Akter, Mst Shapna
Software Engineering
Computation and Language
Automated detection of software vulnerabilities is critical for enhancing security, yet existing methods often struggle with the complexity and diversity of modern codebases. In this paper, we introduce EnStack, a novel ensemble stacking framework that enhances vulnerability detection using natural language processing (NLP) techniques. Our approach synergizes multiple pre-trained large language models (LLMs) specialized in code understanding CodeBERT for semantic analysis, GraphCodeBERT for structural representation, and UniXcoder for cross-modal capabilities. By fine-tuning these models on the Draper VDISC dataset and integrating their outputs through meta-classifiers such as Logistic Regression, Support Vector Machines (SVM), Random Forest, and XGBoost, EnStack effectively captures intricate code patterns and vulnerabilities that individual models may overlook. The meta-classifiers consolidate the strengths of each LLM, resulting in a comprehensive model that excels in detecting subtle and complex vulnerabilities across diverse programming contexts. Experimental results demonstrate that EnStack significantly outperforms existing methods, achieving notable improvements in accuracy, precision, recall, and F1-score. This work highlights the potential of ensemble LLM approaches in code analysis tasks and offers valuable insights into applying NLP techniques for advancing automated vulnerability detection.
title EnStack: An Ensemble Stacking Framework of Large Language Models for Enhanced Vulnerability Detection in Source Code
topic Software Engineering
Computation and Language
url https://arxiv.org/abs/2411.16561