An elegant intellectual engine towards automation of blockchain smart contract vulnerability detection
Abstract To prevent vulnerabilities and ensure app security, smart contract vulnerability detection identifies flaws in blockchain code. To overcome the limitations of traditional detection methods, this study introduces a novel approach that combines Explainable Artificial Intelligence (XAI) with D...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-08870-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849766916531421184 |
|---|---|
| author | Balachandar Raju Gayathri Devi K |
| author_facet | Balachandar Raju Gayathri Devi K |
| author_sort | Balachandar Raju |
| collection | DOAJ |
| description | Abstract To prevent vulnerabilities and ensure app security, smart contract vulnerability detection identifies flaws in blockchain code. To overcome the limitations of traditional detection methods, this study introduces a novel approach that combines Explainable Artificial Intelligence (XAI) with Deep Learning (DL) to detect vulnerabilities in smart contracts. The proposed intellectual engine operates in multiple stages. First, a smart contract is created, and the user provides a value during the runtime phase. XAI and DL then analyze the opcodes in high-value contracts to detect potentially risky processes. If violations such as security protocol failures, insufficient funds, or account restrictions are found, the engine halts the transaction and generates an error report. If the contract passes this vulnerability assessment, it continues executing without interruption. This ensures flagged transactions remain functional while being assessed. Our proposed Hybrid Boot Branch and Bound Long Short-Term Memory (HB3LSTM) approach achieves outstanding performance, with an accuracy of 99.68%, precision of 99.43%, recall of 99.54%, and an F1-score of 99.40%, which surpasses the performance of existing methods. |
| format | Article |
| id | doaj-art-cd79a4722b804498a6ee4e7004e95d4e |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-cd79a4722b804498a6ee4e7004e95d4e2025-08-20T03:04:25ZengNature PortfolioScientific Reports2045-23222025-07-0115113210.1038/s41598-025-08870-xAn elegant intellectual engine towards automation of blockchain smart contract vulnerability detectionBalachandar Raju0Gayathri Devi K1Department of Computer Science and Engineering, Pollachi Institute of Engineering and TechnologyDepartment of Electronics and Communication Engineering, Dr. N.G.P Institute of TechnologyAbstract To prevent vulnerabilities and ensure app security, smart contract vulnerability detection identifies flaws in blockchain code. To overcome the limitations of traditional detection methods, this study introduces a novel approach that combines Explainable Artificial Intelligence (XAI) with Deep Learning (DL) to detect vulnerabilities in smart contracts. The proposed intellectual engine operates in multiple stages. First, a smart contract is created, and the user provides a value during the runtime phase. XAI and DL then analyze the opcodes in high-value contracts to detect potentially risky processes. If violations such as security protocol failures, insufficient funds, or account restrictions are found, the engine halts the transaction and generates an error report. If the contract passes this vulnerability assessment, it continues executing without interruption. This ensures flagged transactions remain functional while being assessed. Our proposed Hybrid Boot Branch and Bound Long Short-Term Memory (HB3LSTM) approach achieves outstanding performance, with an accuracy of 99.68%, precision of 99.43%, recall of 99.54%, and an F1-score of 99.40%, which surpasses the performance of existing methods.https://doi.org/10.1038/s41598-025-08870-xBlockchainBranch and bound optimizationDeep learningOpcodeSmart contractVulnerability detection |
| spellingShingle | Balachandar Raju Gayathri Devi K An elegant intellectual engine towards automation of blockchain smart contract vulnerability detection Scientific Reports Blockchain Branch and bound optimization Deep learning Opcode Smart contract Vulnerability detection |
| title | An elegant intellectual engine towards automation of blockchain smart contract vulnerability detection |
| title_full | An elegant intellectual engine towards automation of blockchain smart contract vulnerability detection |
| title_fullStr | An elegant intellectual engine towards automation of blockchain smart contract vulnerability detection |
| title_full_unstemmed | An elegant intellectual engine towards automation of blockchain smart contract vulnerability detection |
| title_short | An elegant intellectual engine towards automation of blockchain smart contract vulnerability detection |
| title_sort | elegant intellectual engine towards automation of blockchain smart contract vulnerability detection |
| topic | Blockchain Branch and bound optimization Deep learning Opcode Smart contract Vulnerability detection |
| url | https://doi.org/10.1038/s41598-025-08870-x |
| work_keys_str_mv | AT balachandarraju anelegantintellectualenginetowardsautomationofblockchainsmartcontractvulnerabilitydetection AT gayathridevik anelegantintellectualenginetowardsautomationofblockchainsmartcontractvulnerabilitydetection AT balachandarraju elegantintellectualenginetowardsautomationofblockchainsmartcontractvulnerabilitydetection AT gayathridevik elegantintellectualenginetowardsautomationofblockchainsmartcontractvulnerabilitydetection |