• e - ISSN No : 2832-4277
Submit Paper
IJRTTE Logo

INTERNATIONAL JOURNAL OF RECENT TRENDS IN TECHNOLOGY AND ENGINEERING (IJRTTE)

Home / Archives / Vol. 4 No. 3 / Articles

LLM-Driven Cross-Chain Smart Contract Auditing Framework for Secure Web3 Interoperability

Anil Kumar
Research Scholar, Department of Education, Chhatrapati Shahu JI Maharaj University , India.
P.K .Anjani
Professor, Department of Management Studies, Sona College of Technology, Salem , India.
Bechoo Lal
Associate Professor, Department of Computer Science and Engineering, India.

Keywords: Smart Contracts, Cross-Chain Security, Large Language Models, Blockchain Interoperability, Vulnerability Detection, Web3 Security.

Abstract

The swift spread of blockchain ecosystems and the interoperability of cross-chainsm has presented difficult security problematic issues that cannot be successfully solved using advanced smart contract auditing instruments. The current methods are usually applied to single-chain settings and are not designed to study the vulnerabilities that emerge due to cross-chain interactions, bridge strategies, and models of heterogeneous implementation. In order to overcome these drawbacks, this paper suggests an LLM-powered Cross-Chain Smart Contract Auditing Framework to ensure secure and scalable Web3 interoperability. The framework proposed unites a Cross-Chain Contract Abstraction Layer (CCCAL) to standardize smart contracts across blockchains of different types and uses a fine-tuned Large Language Model (LLM) to do semantic vulnerability checks, cross-chain dependency analysis, and attack reasoning. In contrast to the traditional tools, the framework determines the code-level, logic-level, bridge-level, and interoperability-induced vulnerabilities. New Cross-Chain Risk Index (CRI) is presented to measure security risk using a quantitative model of the risk exploitability, attack propagation, and financial consequences. The results of numerous experiments are performed on multi-chain datasets that prove the superiority of the proposed system with a vulnerability detection rate of 96.8, large cross-chain attacks detection rates, and a low number of false positives when compared to the current tools. These findings verify the efficiency, scale, and real-world usability of the framework, resulting in it being a strong framework to use to achieve next-generation cross-chain and
Web3 ecosystems.
PDF
Download Certificate
Details
Published
2025-09-30
Pages
1-11
Issue
Vol. 4 No. 3 (2025): IJRTTE - 04 - 03
Section
Articles

References

  1. Mandana, E., Vlahavas, G., & Vakali, A. (2025). EVuLLM: Ethereum smart contract vulnerability detection using large language models. Electronics, 14(16), 3226. https://doi.org/10.3390/electronics14163226
  2. Wei, Z., et al. (2025). Advanced smart contract vulnerability detection via LLM-powered multi-agent systems. IEEE Transactions on Software Engineering, 51(10), 2830–2846. https://doi.org/10.1109/TSE.2025.3597319
  3. Choi, R.-Y., Song, Y., Jang, M., Kim, T., Ahn, J., & Im, D.-H. (2025). Smart contract vulnerability detection using large language models and graph structural analysis. Computers, Materials & Continua, 83(1), 785–801. https://doi.org/10.32604/cmc.2025.061185
  4. Boi, B., Esposito, C., & Lee, S. (2024). Smart contract vulnerability detection: The role of large language model (LLM). ACM SIGAPP Applied Computing Review, 24(3), 19–29. https://doi.org/10.1145/3687251.3687253
  5. Wang, L., Zhao, Y., Wang, K., Zhang, Z., & Zhang, W. (2024). VulnScan GPT: A new framework for smart contract vulnerability detection combining vector database and GPT model. Journal of Surveillance, Security and Safety, 5(4), 258–272. https://doi.org/10.20517/jsss.2024.21
  6. Su, I. F., Wang, S. M., Chung, Y. C., & Tsai, Y. H. (2026). A smart contract vulnerability detection manner based on large language model. In T. H. Meen, C. F. Yang, & C. Y. Chang (Eds.), Proceedings of the 7th International Conference on Knowledge Innovation and Invention, Volume 1. ICKII 2024. Lecture Notes in Electrical Engineering (Vol. 1481). Springer. https://doi.org/10.1007/978-981-95-2113-5_2
  7. Hu, S., Huang, T., Ilhan, F., Tekin, S., & Liu, L. (2023, November). Large language model-powered smart contract vulnerability detection: New perspectives. In Proceedings of the IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA) (pp. 297–306). IEEE. https://doi.org/10.1109/TPS-ISA58951.2023.00044
  8. Huang, H., Guo, L., Zhao, L., Wang, H., Xu, C., & Jiang, S. (2024). Effective combining source code and opcode for accurate vulnerability detection of smart contracts in edge AI systems. Applied Soft Computing, 158, 111556. https://doi.org/10.1016/j.asoc.2024.111556
  9. Deng, W., Wei, H., Huang, T., Cao, C., Peng, Y., & Hu, X. (2023). Smart contract vulnerability detection based on deep learning and multimodal decision fusion. Sensors, 23(16), 7246. https://doi.org/10.3390/s23167246
  10. Li, W., Liu, Z., Chen, J., Liu, Z., & He, Q. (2025). Towards blockchain interoperability: A comprehensive survey on cross-chain solutions. Blockchain: Research and Applications, 6(3), 100286. https://doi.org/10.1016/j.bcra.2025.100286
  11. Ren, K., et al. (2023). Interoperability in blockchain: A survey. IEEE Transactions on Knowledge and Data Engineering, 35(12), 12750–12769. https://doi.org/10.1109/TKDE.2023.3275220
  12. Li, N., Qi, M., Xu, Z., Zhu, X., Zhou, W., Wen, S., & Xiang, Y. (2024). Blockchain cross-chain bridge security: Challenges, solutions, and future outlook. Distributed Ledger Technologies: Research and Practice, 4. https://doi.org/10.1145/3696429
  13. Notland, J. S., Li, J., Nowostawski, M., & Haro, P. H. (2025). SoK: Cross-chain bridging architectural design flaws and mitigations. Blockchain: Research and Applications, 6, 100315. https://doi.org/10.1016/j.bcra.2025.100315
  14. Cheng, L., Lv, Z., Alfarraj, O., Tolba, A., Yu, X., & Ren, Y. (2024). Secure cross-chain interaction solution in multi-blockchain environment. Heliyon, 10(7), e28861. https://doi.org/10.1016/j.heliyon.2024.e28861
  15. Jia, L., Shao, B., & Bian, G. (2025). Cross-chain technology of consortium blockchain based on identity authentication. Electronics, 14(6), 1185. https://doi.org/10.3390/electronics14061185
  16. Mukherjee, A., Olivieri, L., Chaki, N., & Cortesi, A. (2025). Double-spending attacks in cross-blockchain ecosystems. Blockchain: Research and Applications, 6, 100378. https://doi.org/10.1016/j.bcra.2025.100378
  17. Eshghie, M., Artho, C., Stammler, H., Ahrendt, W., Hildebrandt, T. T., & Schneider, G. (2024). HighGuard: Cross-chain business logic monitoring of smart contracts. In Proceedings of the 2024 39th IEEE/ACM International Conference on Automated Software Engineering (ASE) (pp. 2378–2381).