NASC: Neuro-symbolic Architecture for Smart Contracts Vulnerability Detection

• Cleidimar L. dos Passos UFV
• Josué N. Campos UFV
• Luís H. S. de Carvalho UFV
• Matheus J. da Silva UFV
• José A. M. Nacif UFV

DOI: https://doi.org/10.5753/sast.2026.31443

Resumo

Smart contracts control digital assets under conditions of immutability in blockchain networks, making vulnerability detection an important task in decentralized systems security. Traditional static analysis tools generally rely on specific syntactic patterns, which can make it difficult for developers to interpret the results. This work presents NASC, a Neuro-symbolic agent architecture for vulnerability analysis in Solidity smart contracts. The approach combines a language model-based planner agent, a symbolic core responsible for converting the source code into first-order logic facts, and an LLM agent orchestration module based on the BMAD (Build More Architect Dreams) method that enables the agent to read, write, and run the symbolic core of NASC. The detection mechanism is performed by declarative rules implemented in Prolog, while an analyst agent transforms the results into structured natural language reports. The architecture was evaluated using three literature datasets. Our results show that NASC is capable of identifying different vulnerability patterns and producing interpretable reports, achieving over 80% of recall in 2 of 3 datasets analyzed. Furthermore, the study highlights the potential of integrating logical inference and language model-based agents to support security analysis processes.

Palavras-chave: Neuro-symbolic AI, Smart Contracts, Vulnerability Detection

Referências

Tegan Brennan, Ruoyu Zhang, Arnab Banerjee, and Manuel Egele. 2022. Sailfish: Vetting smart contract state-inconsistency bugs via graph-based-and-propertydirected symbolic execution. In 2022 IEEE Symposium on Security and Privacy (SP). IEEE, 1211–1226.

Fabio Ceolin. 2026. The Edge Agent: A Neurosymbolic Framework for Autonomous Edge AI Agents. [link]

Stefanos Chaliasos, Marcos Antonios Charalambous, Liyi Zhou, Rafaila Galanopoulou, Arthur Gervais, Dimitris Mitropoulos, and Benjamin Livshits. 2024. Smart contract and defi security tools: Do they meet the needs of practitioners?. In Proceedings of the 46th IEEE/ACM International Conference on Software Engineering. 1–13.

Jaeseung Choi, Joonun Kim, Byungho Kim, Jiho Shin, and Sang Kil Cha. 2021. Smartian: Enhancing smart contract fuzzing with static and dynamic data-flow analysis. In Proceedings of the 36th IEEE/ACM International Conference on Automated Software Engineering (ASE). 548–560.

Young-Woo Choi, Tae-Eun Kim, Jin-Woo Hong, Chang-Seo Song, and Hyoung-Shik Kim. 2023. eTainter: Detecting Gas-Guzzling Vulnerabilities in Smart Contracts. In Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA).

ConsenSys Diligence. 2026. Mythril: Security analysis tool for Ethereum smart contracts. [link]

Isaac David, Liyi Zhou, Kaihua Qin, Dawn Song, Lorenzo Cavallaro, and Arthur Gervais. 2023. Do you still need a manual smart contract audit? arXiv preprint arXiv:2306.12338 (2023).

Monika di Angelo, Thomas Durieux, João F. Ferreira, and Gernot Salzer. 2023. SmartBugs 2.0: An Execution Framework for Weakness Detection in Ethereum Smart Contracts. arXiv:2306.05057 [cs.CR] [link]

Josselin Feist, Gustavo Grieco, and Alex Groce. 2019. Slither: a static analysis framework for smart contracts. In 2019 IEEE/ACM 2nd international workshop on emerging trends in software engineering for blockchain (WETSEB). IEEE, 8–15.

Gustavo Grieco, Alex Groce, Josselin Feist, and Trail of Bits. 2020. Echidna: A Fast Smart Contract Fuzzer. [link]

Daojing He, Zhi Deng, Yuxing Zhang, Sammy Chan, Yao Cheng, and Nadra Guizani. 2020. Smart contract vulnerability analysis and security audit. IEEE Network 34, 5 (2020), 276–282.

Brian Madison and BMad Code Org. 2026. BMAD-METHOD: Breakthrough Method for Agile Ai Driven Development. Acessado em: 2026-06-30.

Uzma Nawaz, Mufti Anees-ur Rahaman, and Zubair Saeed. 2025. A review of neuro-symbolic AI integrating reasoning and learning for advanced cognitive systems. Intelligent Systems with Applications 26 (2025), 200541.

Hoang H. Nguyen, Nhat-Minh Nguyen, Chunyao Xie, Zahra Ahmadi, Daniel Kudendo, Thanh-Nam Doan, and Lingxiao Jiang. 2023. MANDO-HGT: Heterogeneous Graph Transformers for Smart Contract Vulnerability Detection. In 2023 IEEE/ACM 20th International Conference on Mining Software Repositories (MSR). 334–346. DOI: 10.1109/MSR59073.2023.00052

Hadis Rezaei, Mojtaba Eshghie, Karl Andersson, and Francesco Palmieri. 2025. SoK: Root Cause of $1 Billion Loss in Smart Contract Real-World Attacks via a Systematic Literature Review of Vulnerabilities. arXiv preprint arXiv:2507.20175 (2025). arXiv:2507.20175 [cs.CR] [link]

Zibin Zheng, Jianzhong Su, Jiachi Chen, David Lo, Zhijie Zhong, and Mingxi Ye. 2024. DAppSCAN: Building Large-Scale Datasets for Smart Contract Weaknesses in DApp Projects. IEEE Transactions on Software Engineering 50, 6 (2024), 1360–1373. DOI: 10.1109/tse.2024.3383422