SAEL: Leveraging Large Language Models with Adaptive Mixture-of-Experts for Smart Contract Vulnerability Detection

TL;DR

SAEL is a novel framework that combines large language models with an adaptive mixture-of-experts architecture to improve smart contract vulnerability detection, outperforming existing methods in accuracy and generalization.

Contribution

The paper introduces SAEL, integrating LLMs with a dynamic mixture-of-experts approach for enhanced vulnerability detection in smart contracts, addressing limitations of static and specialized models.

Findings

SAEL outperforms existing detection methods across various vulnerabilities.

The adaptive mixture-of-experts architecture improves feature integration and detection accuracy.

Prompt-tuning enhances LLM-based vulnerability identification.

Abstract

With the increasing security issues in blockchain, smart contract vulnerability detection has become a research focus. Existing vulnerability detection methods have their limitations: 1) Static analysis methods struggle with complex scenarios. 2) Methods based on specialized pre-trained models perform well on specific datasets but have limited generalization capabilities. In contrast, general-purpose Large Language Models (LLMs) demonstrate impressive ability in adapting to new vulnerability patterns. However, they often underperform on specific vulnerability types compared to methods based on specialized pre-trained models. We also observe that explanations generated by general-purpose LLMs can provide fine-grained code understanding information, contributing to improved detection performance. Inspired by these observations, we propose SAEL, an LLM-based framework for smart contract vulnerability detection. We first design targeted prompts to guide LLMs in identifying vulnerabilities and generating explanations, which serve as prediction features. Next, we apply prompt-tuning on CodeT5 and T5 to process contract code and explanations, enhancing task-specific performance. To combine the strengths of each approach, we introduce an Adaptive Mixture-of-Experts architecture. This dynamically adjusts feature weights via a Gating Network, which selects relevant features using TopK filtering and Softmax normalization, and incorporates a Multi-Head Self-Attention mechanism to enhance cross-feature relationships. This design enables effective integration of LLM predictions, explanation features, and code features through gradient optimization. The loss function jointly considers both independent feature performance and overall weighted predictions. Experiments show that SAEL outperforms existing methods across various vulnerabilities.