Decoupled Smart Contract Audits: Lightweight LLM Framework via Distillation and Aggregation

arXiv:2606.0312852.5Has Code
Predicted impact top 37% in CR · last 90 daysOriginality Incremental advance
AI Analysis

For blockchain security practitioners, this provides an efficient, accurate auditing tool that reduces reliance on massive LLMs, though the approach is incremental.

The paper introduces a lightweight LLM framework (0.6B-4B parameters) for smart contract auditing that decouples tasks into vulnerability detection, explanation, severity classification, and remediation. It achieves 98.25% detection accuracy and outperforms larger models (7B-34B) while reducing computational overhead.

Smart contracts face critical security challenges that require thorough auditing in decentralized web services. While Large Language Models (LLMs) have shown promise in automated vulnerability detection, existing approaches lack severity evaluations with actionable remediation and demand unnecessarily massive computational overhead. In this study, we introduce an efficient end-to-end smart contract security audit framework utilizing lightweight, highly optimized open-source LLMs (0.6B-4B parameters). Our framework decouples comprehensive audit tasks into four interconnected components: vulnerability detection, explanation, severity classification, and remediation recommendation. To maintain high accuracy without massive parameters, we implement Rank-Stabilized Low-Rank Adapters (rsLoRA), knowledge distillation, and a custom Chain-of-Verification (CoVe) aggregation strategy to systematically screen and consolidate multiple draft responses from the model into a highly accurate audit report. Experimental results demonstrate that our lightweight pipeline consistently outperforms state-of-the-art open-source coder dense LLMs (7B to 34B parameters), achieving 98.25% accuracy in vulnerability detection and an alignment score of 0.4375 in generative explanation tasks. Furthermore, our extensive ablation studies empirically validate the superiority of our decoupled audit processes over unified prompting and uncover a novel severity centrality bias, establishing a critical benchmark for future research in LLM-assisted auditing.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes