Malicious Contract Detection for Blockchain Network Using Lightweight Deep Learning Implemented through Explainable AI
A smart contract is a digital contract on a blockchain. Through smart contracts, transactions between parties are possible without a third party on the blockchain network. However, there are malicious contracts, such as greedy contracts, which can cause enormous damage to users and blockchain networ...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/18/3893 |
| _version_ | 1797580470424174592 |
|---|---|
| author | Yeajun Kang Wonwoong Kim Hyunji Kim Minwoo Lee Minho Song Hwajeong Seo |
| author_facet | Yeajun Kang Wonwoong Kim Hyunji Kim Minwoo Lee Minho Song Hwajeong Seo |
| author_sort | Yeajun Kang |
| collection | DOAJ |
| description | A smart contract is a digital contract on a blockchain. Through smart contracts, transactions between parties are possible without a third party on the blockchain network. However, there are malicious contracts, such as greedy contracts, which can cause enormous damage to users and blockchain networks. Therefore, countermeasures against this problem are required. In this work, we propose a greedy contract detection system based on deep learning. The detection model is trained through the frequency of opcodes in the smart contract. Additionally, we implement Gredeeptector, a lightweight model for deployment on the IoT. We identify important instructions for detection through explainable artificial intelligence (XAI). After that, we train the Greedeeptector through only important instructions. Therefore, Greedeeptector is a computationally and memory-efficient detection model for the IoT. Through our approach, we achieve a high detection accuracy of 92.3%. In addition, the file size of the lightweight model is reduced by 41.5% compared to the base model and there is little loss of accuracy. |
| first_indexed | 2024-03-10T22:50:28Z |
| format | Article |
| id | doaj.art-a4644805f6104d90ba9e35e3fe26b35b |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T22:50:28Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-a4644805f6104d90ba9e35e3fe26b35b2023-11-19T10:22:50ZengMDPI AGElectronics2079-92922023-09-011218389310.3390/electronics12183893Malicious Contract Detection for Blockchain Network Using Lightweight Deep Learning Implemented through Explainable AIYeajun Kang0Wonwoong Kim1Hyunji Kim2Minwoo Lee3Minho Song4Hwajeong Seo5Division of IT Convergence Engineering, Hansung University, Seoul 02876, Republic of KoreaDivision of IT Convergence Engineering, Hansung University, Seoul 02876, Republic of KoreaDivision of IT Convergence Engineering, Hansung University, Seoul 02876, Republic of KoreaDivision of IT Convergence Engineering, Hansung University, Seoul 02876, Republic of KoreaDivision of IT Convergence Engineering, Hansung University, Seoul 02876, Republic of KoreaDivision of IT Convergence Engineering, Hansung University, Seoul 02876, Republic of KoreaA smart contract is a digital contract on a blockchain. Through smart contracts, transactions between parties are possible without a third party on the blockchain network. However, there are malicious contracts, such as greedy contracts, which can cause enormous damage to users and blockchain networks. Therefore, countermeasures against this problem are required. In this work, we propose a greedy contract detection system based on deep learning. The detection model is trained through the frequency of opcodes in the smart contract. Additionally, we implement Gredeeptector, a lightweight model for deployment on the IoT. We identify important instructions for detection through explainable artificial intelligence (XAI). After that, we train the Greedeeptector through only important instructions. Therefore, Greedeeptector is a computationally and memory-efficient detection model for the IoT. Through our approach, we achieve a high detection accuracy of 92.3%. In addition, the file size of the lightweight model is reduced by 41.5% compared to the base model and there is little loss of accuracy.https://www.mdpi.com/2079-9292/12/18/3893smart contractgreedy contract detectiondeep learningexplainable artificial intelligencelightweight |
| spellingShingle | Yeajun Kang Wonwoong Kim Hyunji Kim Minwoo Lee Minho Song Hwajeong Seo Malicious Contract Detection for Blockchain Network Using Lightweight Deep Learning Implemented through Explainable AI Electronics smart contract greedy contract detection deep learning explainable artificial intelligence lightweight |
| title | Malicious Contract Detection for Blockchain Network Using Lightweight Deep Learning Implemented through Explainable AI |
| title_full | Malicious Contract Detection for Blockchain Network Using Lightweight Deep Learning Implemented through Explainable AI |
| title_fullStr | Malicious Contract Detection for Blockchain Network Using Lightweight Deep Learning Implemented through Explainable AI |
| title_full_unstemmed | Malicious Contract Detection for Blockchain Network Using Lightweight Deep Learning Implemented through Explainable AI |
| title_short | Malicious Contract Detection for Blockchain Network Using Lightweight Deep Learning Implemented through Explainable AI |
| title_sort | malicious contract detection for blockchain network using lightweight deep learning implemented through explainable ai |
| topic | smart contract greedy contract detection deep learning explainable artificial intelligence lightweight |
| url | https://www.mdpi.com/2079-9292/12/18/3893 |
| work_keys_str_mv | AT yeajunkang maliciouscontractdetectionforblockchainnetworkusinglightweightdeeplearningimplementedthroughexplainableai AT wonwoongkim maliciouscontractdetectionforblockchainnetworkusinglightweightdeeplearningimplementedthroughexplainableai AT hyunjikim maliciouscontractdetectionforblockchainnetworkusinglightweightdeeplearningimplementedthroughexplainableai AT minwoolee maliciouscontractdetectionforblockchainnetworkusinglightweightdeeplearningimplementedthroughexplainableai AT minhosong maliciouscontractdetectionforblockchainnetworkusinglightweightdeeplearningimplementedthroughexplainableai AT hwajeongseo maliciouscontractdetectionforblockchainnetworkusinglightweightdeeplearningimplementedthroughexplainableai |