Towards Secure and Explainable Smart Contract Generation with Security-Aware Group Relative Policy Optimization

• URL: http://arxiv.org/abs/2509.09942v2
• Date: Sun, 12 Oct 2025 04:04:06 GMT
• Title: Towards Secure and Explainable Smart Contract Generation with Security-Aware Group Relative Policy Optimization
• Authors: Lei Yu, Jingyuan Zhang, Xin Wang, Jiajia Ma, Li Yang, Fengjun Zhang,
• Abstract summary: We propose SmartCoder-R1, a framework for secure and explainable smart contract generation.<n>We train the model to emulate human security analysis.<n>SmartCoder-R1 establishes a new state of the art, achieving top performance across five key metrics.
• Score: 18.013438474903314
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Smart contracts automate the management of high-value assets, where vulnerabilities can lead to catastrophic financial losses. This challenge is amplified in Large Language Models (LLMs) by two interconnected failures: they operate as unauditable "black boxes" lacking a transparent reasoning process, and consequently, generate code riddled with critical security vulnerabilities. To address both issues, we propose SmartCoder-R1 (based on Qwen2.5-Coder-7B), a novel framework for secure and explainable smart contract generation. It begins with Continual Pre-training (CPT) to specialize the model. We then apply Long Chain-of-Thought Supervised Fine-Tuning (L-CoT SFT) on 7,998 expert-validated reasoning-and-code samples to train the model to emulate human security analysis. Finally, to directly mitigate vulnerabilities, we employ Security-Aware Group Relative Policy Optimization (S-GRPO), a reinforcement learning phase that refines the generation policy by optimizing a weighted reward signal for compilation success, security compliance, and format correctness. Evaluated against 17 baselines on a benchmark of 756 real-world functions, SmartCoder-R1 establishes a new state of the art, achieving top performance across five key metrics: a ComPass of 87.70%, a VulRate of 8.60%, a SafeAval of 80.16%, a FuncRate of 53.84%, and a FullRate of 50.53%. This FullRate marks a 45.79% relative improvement over the strongest baseline, DeepSeek-R1. Crucially, its generated reasoning also excels in human evaluations, achieving high-quality ratings for Functionality (82.7%), Security (85.3%), and Clarity (90.7%).

Related papers

• Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away [97.11976870616273]
  We propose a lightweight inference-time defense that treats safety recovery as a satising constraint rather than an objective.<n>In our evaluations across six open-source MLRMs and four jailbreak benchmarks, SafeThink reduces attack success rates by 30-60%.
  arXiv  Detail & Related papers  (2026-02-11T18:09:17Z)
• Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model [60.60587869092729]
  Large language models (LLMs) are increasingly used in software development, yet their tendency to generate insecure code remains a major barrier to real-world deployment.<n>We propose SecCoderX, an online reinforcement learning framework for functionality-preserving secure code generation.
  arXiv  Detail & Related papers  (2026-02-07T07:42:07Z)
• CVeDRL: An Efficient Code Verifier via Difficulty-aware Reinforcement Learning [57.24524263804788]
  Code verifiers play a critical role in post-verification for LLM-based code generation.<n>Existing supervised fine-tuning methods suffer from data scarcity, high failure rates, and poor inference efficiency.<n>We show that naive RL with only functionality rewards fails to generate effective unit tests for difficult branches and samples.
  arXiv  Detail & Related papers  (2026-01-30T10:33:29Z)
• Categorical Framework for Quantum-Resistant Zero-Trust AI Security [0.0]
  We present a novel integration of post-quantum cryptography (PQC) and zero trust architecture (AZT) to secure AI model.<n>Our framework uniquely models cryptographic access as morphisms and trust policies as functors.<n>We demonstrate its efficacy through a concrete ESP32-based implementation.
  arXiv  Detail & Related papers  (2025-11-25T17:17:24Z)
• SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models [66.71948519280669]
  Multimodal Large Reasoning Models (MLRMs) demonstrate impressive crossmodal reasoning but often amplify safety risks under adversarial prompts.<n> Existing defenses mainly act at the output level and do not constrain the reasoning process, leaving models to implicit risks.<n>We propose SaFeR-VLM, which integrates four components and supports dynamic and interpretable safety decisions beyond surface-level filtering.
  arXiv  Detail & Related papers  (2025-10-08T10:39:12Z)
• A Systematic Evaluation of Parameter-Efficient Fine-Tuning Methods for the Security of Code LLMs [14.754759160027959]
  Large Language Models (LLMs) significantly accelerate software development, but their frequent generation of insecure code presents serious risks.<n>We present a comprehensive evaluation of seven parameter-efficient fine-tuning (PEFT) techniques, demonstrating substantial gains in secure code generation without compromising functionality.<n>Our research identifies prompt-tuning as the most effective PEFT method, achieving an 80.86% Overall-Secure-Rate on CodeGen2 16B, a 13.5-point improvement over the 67.28% baseline.
  arXiv  Detail & Related papers  (2025-09-16T04:09:41Z)
• PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality [41.04710068888387]
  PRISM (Principled Reasoning for Integrated Safety in Multimodality) is a system2-like framework that aligns vision-language models (VLMs)<n>Our framework consists of two key components: PRISM-CoT, a dataset that teaches safety-aware chain-of-thought reasoning, and PRISM-DPO, generated via Monte Carlo Tree Search (MCTS)<n> Comprehensive evaluations demonstrate PRISM's effectiveness, achieving remarkably low attack success rates including 0.15% on JailbreakV-28K for Qwen2-VL and 90% improvement over the previous best method on VLBreak for LLaVA-1.5.
  arXiv  Detail & Related papers  (2025-08-26T03:45:19Z)
• MalCodeAI: Autonomous Vulnerability Detection and Remediation via Language Agnostic Code Reasoning [0.0]
  MalCodeAI is a language-agnostic pipeline for autonomous code security analysis and remediation.<n>It combines code decomposition and semantic reasoning using finetuned Qwen2.5-Coder-3B-Instruct models.<n>MalCodeAI supports red-hat-style exploit tracing, CVSS-based risk scoring, and zero-shot generalization to detect complex, zero-day vulnerabilities.
  arXiv  Detail & Related papers  (2025-07-15T01:25:04Z)
• Decompiling Smart Contracts with a Large Language Model [51.49197239479266]
  Despite Etherscan's 78,047,845 smart contracts deployed on (as of May 26, 2025), a mere 767,520 ( 1%) are open source.<n>This opacity necessitates the automated semantic analysis of on-chain smart contract bytecode.<n>We introduce a pioneering decompilation pipeline that transforms bytecode into human-readable and semantically faithful Solidity code.
  arXiv  Detail & Related papers  (2025-06-24T13:42:59Z)
• A Preference-Driven Methodology for High-Quality Solidity Code Generation [11.139579355590332]
  We propose textbfmytitle, a novel framework that extends standard DPO beyond human preferences to incorporate quantifiable blockchain-specific metrics.<n>Our framework introduces a comprehensive evaluation methodology with four complementary metrics: Pass@k (functional correctness), Compile@k (syntactic correctness), Gas@k (gas efficiency), and Secure@k (security assessment)<n>Our framework significantly outperforms existing approaches across all critical dimensions, achieving 66.7% Pass@5, 58.9% Gas@5, and 62.5% Secure@5.
  arXiv  Detail & Related papers  (2025-06-03T15:45:31Z)
• CyberGym: Evaluating AI Agents' Cybersecurity Capabilities with Real-World Vulnerabilities at Scale [46.76144797837242]
  Large language model (LLM) agents are becoming increasingly skilled at handling cybersecurity tasks autonomously.<n>Existing benchmarks fall short, often failing to capture real-world scenarios or being limited in scope.<n>We introduce CyberGym, a large-scale and high-quality cybersecurity evaluation framework featuring 1,507 real-world vulnerabilities.
  arXiv  Detail & Related papers  (2025-06-03T07:35:14Z)
• AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security [74.22452069013289]
  AegisLLM is a cooperative multi-agent defense against adversarial attacks and information leakage.<n>We show that scaling agentic reasoning system at test-time substantially enhances robustness without compromising model utility.<n> Comprehensive evaluations across key threat scenarios, including unlearning and jailbreaking, demonstrate the effectiveness of AegisLLM.
  arXiv  Detail & Related papers  (2025-04-29T17:36:05Z)
• Enhancing Smart Contract Vulnerability Detection in DApps Leveraging Fine-Tuned LLM [0.7018579932647147]
  Decentralized applications (DApps) face significant security risks due to vulnerabilities in smart contracts.<n>This paper proposes a novel approach leveraging fine-tuned Large Language Models (LLMs) to enhance smart contract vulnerability detection.
  arXiv  Detail & Related papers  (2025-04-07T12:32:14Z)
• SmartLLM: Smart Contract Auditing using Custom Generative AI [0.0]
  This paper introduces SmartLLM, a novel approach leveraging fine-tuned LLaMA 3.1 models with Retrieval-Augmented Generation (RAG)<n>By integrating domain-specific knowledge from ERC standards, SmartLLM achieves superior performance compared to static analysis tools like Mythril and Slither.<n> Experimental results demonstrate a perfect recall of 100% and an accuracy score of 70%, highlighting the model's robustness in identifying vulnerabilities.
  arXiv  Detail & Related papers  (2025-02-17T06:22:05Z)
• Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models [60.38983114420845]
  We propose dual risk minimization (DRM) to better preserve the core features of downstream tasks.<n>DRM balances expected performance and worst-case performance, establishing a new state of the art on various real-world benchmarks.
  arXiv  Detail & Related papers  (2024-11-29T15:01:25Z)
• G$^2$uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clustering [116.4277292854053]
  Federated Learning (FL) offers collaborative model training without data sharing. FL is vulnerable to backdoor attacks, where poisoned model weights lead to compromised system integrity. We present G$2$uardFL, a protective framework that reinterprets the identification of malicious clients as an attributed graph clustering problem.
  arXiv  Detail & Related papers  (2023-06-08T07:15:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.