Tailored Prompts, Targeted Protection: Vulnerability-Specific LLM Analysis for Smart Contracts
For blockchain security practitioners, this provides a flexible, high-recall detection method that reduces reliance on manual rules, though it is incremental over existing LLM-based approaches.
The paper tackles smart contract vulnerability detection by proposing an LLM-based framework that uses AST-based context extraction and vulnerability-specific prompts, achieving an average positive recall of 0.92 and negative recall of 0.85 across 13 vulnerability categories on a new dataset of 31,165 instances.
Smart contracts on blockchains are prone to diverse security vulnerabilities that can lead to significant financial losses due to their immutable nature. Existing detection approaches often lack flexibility across vulnerability types and rely heavily on manually crafted expert rules. In this paper, we present an LLM-based framework for practical smart contract vulnerability detection. We construct and release a large-scale dataset comprising 31,165 professionally annotated vulnerability instances collected from over 3,200 real-world projects across 15 major blockchain platforms. Our approach leverages precise AST-based context extraction and vulnerability-specific prompt design to instantiate customized detectors for 13 prevalent vulnerability categories. Experimental results demonstrate strong effectiveness, achieving an average positive recall of 0.92 and an average negative recall of 0.85, highlighting the potential of carefully engineered contextual prompting for scalable and high-precision smart contract security analysis.