Enhancing smart contract security: Leveraging pre‐trained language models for advanced vulnerability detection

Abstract The burgeoning interest in decentralized applications (Dapps), spurred by advancements in blockchain technology, underscores the critical role of smart contracts. However, many Dapp users, often without deep knowledge of smart contracts, face financial risks due to hidden vulnerabilities. T...

Full description

Saved in:
Bibliographic Details
Main Authors: Fei He, Fei Li, Peili Liang
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:IET Blockchain
Subjects:
Online Access:https://doi.org/10.1049/blc2.12072
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850099378258182144
author Fei He
Fei Li
Peili Liang
author_facet Fei He
Fei Li
Peili Liang
author_sort Fei He
collection DOAJ
description Abstract The burgeoning interest in decentralized applications (Dapps), spurred by advancements in blockchain technology, underscores the critical role of smart contracts. However, many Dapp users, often without deep knowledge of smart contracts, face financial risks due to hidden vulnerabilities. Traditional methods for detecting these vulnerabilities, including manual inspections and automated static analysis, are plagued by issues such as high rates of false positives and overlooked security flaws. To combat this, the article introduces an innovative approach using the bidirectional encoder representations from transformers (BERT)‐ATT‐BiLSTM model for identifying potential weaknesses in smart contracts. This method leverages the BERT pre‐trained model to discern semantic features from contract opcodes, which are then refined using a Bidirectional Long Short‐Term Memory Network (BiLSTM) and augmented by an attention mechanism that prioritizes critical features. The goal is to improve the model's generalization ability and enhance detection accuracy. Experiments on various publicly available smart contract datasets confirm the model's superior performance, outperforming previous methods in key metrics like accuracy, F1‐score, and recall. This research not only offers a powerful tool to bolster smart contract security, mitigating financial risks for average users, but also serves as a valuable reference for advancements in natural language processing and deep learning.
format Article
id doaj-art-46f61c31e91c4d4fbfd7a1948ca6390b
institution DOAJ
issn 2634-1573
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series IET Blockchain
spelling doaj-art-46f61c31e91c4d4fbfd7a1948ca6390b2025-08-20T02:40:30ZengWileyIET Blockchain2634-15732024-12-014S154355410.1049/blc2.12072Enhancing smart contract security: Leveraging pre‐trained language models for advanced vulnerability detectionFei He0Fei Li1Peili Liang2College of Blockchain Industry Chengdu University of Information Technology Chengdu Sichuan ChinaCollege of Blockchain Industry Chengdu University of Information Technology Chengdu Sichuan ChinaCollege of Blockchain Industry Chengdu University of Information Technology Chengdu Sichuan ChinaAbstract The burgeoning interest in decentralized applications (Dapps), spurred by advancements in blockchain technology, underscores the critical role of smart contracts. However, many Dapp users, often without deep knowledge of smart contracts, face financial risks due to hidden vulnerabilities. Traditional methods for detecting these vulnerabilities, including manual inspections and automated static analysis, are plagued by issues such as high rates of false positives and overlooked security flaws. To combat this, the article introduces an innovative approach using the bidirectional encoder representations from transformers (BERT)‐ATT‐BiLSTM model for identifying potential weaknesses in smart contracts. This method leverages the BERT pre‐trained model to discern semantic features from contract opcodes, which are then refined using a Bidirectional Long Short‐Term Memory Network (BiLSTM) and augmented by an attention mechanism that prioritizes critical features. The goal is to improve the model's generalization ability and enhance detection accuracy. Experiments on various publicly available smart contract datasets confirm the model's superior performance, outperforming previous methods in key metrics like accuracy, F1‐score, and recall. This research not only offers a powerful tool to bolster smart contract security, mitigating financial risks for average users, but also serves as a valuable reference for advancements in natural language processing and deep learning.https://doi.org/10.1049/blc2.12072artificial intelligenceblockchain applications and digital technologyblockchainscontractsdecentralized applications
spellingShingle Fei He
Fei Li
Peili Liang
Enhancing smart contract security: Leveraging pre‐trained language models for advanced vulnerability detection
IET Blockchain
artificial intelligence
blockchain applications and digital technology
blockchains
contracts
decentralized applications
title Enhancing smart contract security: Leveraging pre‐trained language models for advanced vulnerability detection
title_full Enhancing smart contract security: Leveraging pre‐trained language models for advanced vulnerability detection
title_fullStr Enhancing smart contract security: Leveraging pre‐trained language models for advanced vulnerability detection
title_full_unstemmed Enhancing smart contract security: Leveraging pre‐trained language models for advanced vulnerability detection
title_short Enhancing smart contract security: Leveraging pre‐trained language models for advanced vulnerability detection
title_sort enhancing smart contract security leveraging pre trained language models for advanced vulnerability detection
topic artificial intelligence
blockchain applications and digital technology
blockchains
contracts
decentralized applications
url https://doi.org/10.1049/blc2.12072
work_keys_str_mv AT feihe enhancingsmartcontractsecurityleveragingpretrainedlanguagemodelsforadvancedvulnerabilitydetection
AT feili enhancingsmartcontractsecurityleveragingpretrainedlanguagemodelsforadvancedvulnerabilitydetection
AT peililiang enhancingsmartcontractsecurityleveragingpretrainedlanguagemodelsforadvancedvulnerabilitydetection