SARMF: A Hybrid Framework for Smart Contract Vulnerability Detection and Automated Remediation with Benchmark Evaluation

Abstract

Smart contracts are a core component of blockchain-based decentralized systems, but their immutability and financial exposure make software defects particularly costly. Existing analysis tools have improved vulnerability detection, yet most lack integrated remediation capabilities. This paper presents SARMF, a hybrid framework combining static analysis, pattern detection, lightweight machine learning classification, and template-based remediation. The framework is evaluated using SARMF-Bench, a curated dataset designed to support reproducible assessment of detection and first-pass remediation across common vulnerability classes. Results indicate detection performance in the high-80s to low-90s range with balanced precision and recall, while remediation templates reduce manual correction effort by approximately 30–40%. The contribution is a practical research prototype, a benchmark protocol, and an extensible evaluation framework for smart contract security.