Advanced Approaches for Vulnerability Detection in Solidity-Based Smart Contracts: A Comparative Review

With the advancement of blockchain technology, Solidity-based smart contracts have become essential for automating and securing digital transactions across various sectors, from finance to supply chain management.  These contracts enable decentralized exchanges without intermediaries, enhancing transparency.  However, their immutable nature poses security challenges: any flaw in the code becomes permanent, exposing contracts to attacks and leading to financial and reputational losses.  This paper provides a comparative analysis of recent machine learning (ML) and deep learning (DL) techniques developed for detecting vulnerabilities in Solidity based smart contracts.  By evaluating various approaches, we assess their effectiveness in identifying common threats such as reentrancy attacks and integer overflows.  Finally, we highlight the importance of scalable, AI driven security solutions to address the growing complexity of vulnerabilities.

блокчейн
вразливість
розумний контракт
машинне навчання
глибоке навчання
  1. Sarmah S. S.  Understanding Blockchain Technology.  Computer Science and Engineering (2018).
  2. Tripathi G., Ahad M. A., Casalino G.  A comprehensive review of blockchain technology: Underlying principles and historical background with future challenges.  Decision Analytics Journal.  9, 100344 (2023).
  3. Kushwaha S. S., Joshi S., Singh D., Kaur M., Lee H.-N.  Systematic Review of Security Vulnerabilities in Ethereum Blockchain Smart Contract.  IEEE Access.  10, 6605–6621 (2022).
  4. Aponte-Novoa F. A., Orozco A. L. S., Villanueva-Polanco R., Wightman P.  The 51% Attack on Blockchains: A Mining Behavior Study.  IEEE Access.  9, 1405491–40564 (2021).
  5. Jamwal S., Cano J., Lee G. M., Tran N. H., Truong N.  A survey on Ethereum pseudonymity: Techniques, challenges, and future directions.  Journal of Network and Computer Applications.  232, 104019 (2024).
  6. Hu B., Zhang Z., Liu J. et al.  A comprehensive survey on smart contract construction and execution: paradigms, tools, and systems.  Patterns.  2 (2), 100179 (2021).
  7. Taş R.  Smart Contract Security Vulnerabilities.  Erzincan University Journal of Science and Technology.  16 (1), 196–211 (2023).
  8. Tang X., Zhou K., Cheng J., Li H., Yuan Y.  The Vulnerabilities in Smart Contracts: A Survey.  Advances in Artificial Intelligence and Security. 177–190 (2021).
  9. Feng X., Liu H., Wang L., Zhu H., Sheng V. S.  An interpretable model for large-scale smart contract vulnerability detection.  Blockchain: Research and Applications.  5 (3), 100209 (2024).
  10. Jie W., Chen Q., Wang J., Koe A. S. V. et al.  A novel extended multimodal AI framework towards vulnerability detection in smart contracts.  Information Sciences.  636, 118907 (2023).
  11. Xie X., Wang H., Jian Z., Fang Y., Wang Z., Li T.  Block-gram: Mining knowledgeable features for efficiently smart contract vulnerability detection.  Digital Communications and Networks.  11 (1), 1–12 (2023).
  12. Ren X., Wu Y., Li J., Hao D., Alam M.  Smart contract vulnerability detection based on a semantic code structure and a self-designed neural network.  Computers and Electrical Engineering.  109 (B), 108766 (2023).
  13. Zhang H., Zhang W., Feng Y., Liu Y.  SVScanner: Detecting smart contract vulnerabilities via deep semantic extraction.  Journal of Information Security and Applications.  75, 103484 (2023).
  14. Zhang L., Li Y., Jin T., Wang W. et al.  SPCBIG-EC: A Robust Serial Hybrid Model for Smart Contract Vulnerability Detection.  Sensors.  22 (12), 4621 (2022).
  15. Zhou K., Huang J., Han H., Gong B. et al.  Smart contracts vulnerability detection model based on adversarial multi-task learning.  Journal of Information Security and Applications.  77, 103555 (2023).
  16. Osei S. B., Ma Z., Huang R.  Smart contract vulnerability detection using wide and deep neural network.  Science of Computer Programming.  238, 103172 (2024).
  17. Sun X., Tu L., Zhang J., Cai J., Li B., Wang Y.  ASSBert: Active and semi-supervised bert for smart contract vulnerability detection.  Journal of Information Security and Applications.  73, 103423 (2023).
  18. Cheng J., Chen Y., Cao Y., Wang H.  A vulnerability detection framework with enhanced graph feature learning.  Journal of Systems and Software.  216, 112118 (2024).
  19. Cai J., Li B., Zhang T., Zhang J., Sun X.  Fine-grained smart contract vulnerability detection by heterogeneous code feature learning and automated dataset construction.  Journal of Systems and Software.  209, 111919 (2024).
  20. Wu G., Wang H., Lai X., Wang M., He D., Chan S.  A comprehensive survey of smart contract security: State of the art and research directions.  Journal of Network and Computer Applications.  226, 103882 (2024).
  21. Vidal F. R., Ivaki N., Laranjeiro N.  Vulnerability detection techniques for smart contracts: A systematic literature review.  Journal of Systems and Software.  217, 111919 (2024).
  22. Hu K., Zhu J., Ding Y., Bai X., Huang J.  Smart contract engineering.  Electronics.  9 (12), 2042 (2020).
  23. Aziz R. M., Mahto R., Goel K., Das A., Kumar P., Saxena A.  Modified Genetic Algorithm with Deep Learning for Fraud Transactions of Ethereum Smart Contract.  Applied Sciences.  13 (2), 697 (2023).
  24. Xu G., Liu L., Dong J.  Vulnerability Detection of Ethereum Smart Contract Based on SolBERT-BiGRU-Attention Hybrid Neural Model.  CMES – Computer Modeling in Engineering and Sciences.  137 (1), 903–922 (2023).