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

TL;DR

EnStack is an ensemble framework combining multiple large language models and meta-classifiers to improve automated vulnerability detection in source code, outperforming existing methods in accuracy and robustness.

Contribution

This paper introduces EnStack, a novel ensemble stacking framework that leverages multiple pre-trained LLMs and meta-classifiers for enhanced vulnerability detection in source code.

Findings

EnStack outperforms existing vulnerability detection methods.

The ensemble achieves higher accuracy, precision, recall, and F1-score.

Meta-classifiers effectively combine diverse LLM outputs for better detection.

Abstract

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.