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

Computer Science > Cryptography and Security [Submitted on 2 Jun 2026] Decoupled Smart Contract Audits: Lightweight LLM Framework via Distillation and Aggregation Bagus Rakadyanto Oktavianto Putra, Muhamad Risqi Utama Saputra, Widyawan, Guntur Dharma Putra 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. Comments: 12 pages, 4 figures, 5 tables. Accepted to IEEE ICWS 2026 Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) Cite as: arXiv:2606.03128 [cs.CR]   (or arXiv:2606.03128v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.03128 Focus to learn more Submission history From: Bagus Rakadyanto Oktavianto Putra [view email] [v1] Tue, 2 Jun 2026 04:13:43 UTC (331 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.AI cs.CL cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)