Phishing Detection in Blockchain Transaction Networks Using Ensemble Learning
Abstract
:1. Introduction
1.1. Background and Motivation
1.2. Blockchain Technology
1.3. Blockchain Challenges
1.4. Attacks on Blockchain
1.5. Aims, Novelty, and Contribution
- A novel deep-learning model for detecting phish scams in blockchain transactions is presented.
- Using Bi-LSTM, CNN-LSTM, and embedded-LSTM on the Ethereum transaction network dataset is demonstrated.
2. Literature Review
2.1. Blockchain Technology and Machine Learning
2.2. Blockchain-Based Approach for IoT
2.3. Fraud Detection on the Blockchain Network
2.4. Phishing Scam-Related Studies in Blockchain Transactions
3. Methods
3.1. Dataset
- Tokens List: This list contains information about different tokens built on the Ethereum blockchain. It includes token names, symbols, addresses, decimals, and additional attributes.
- Contracts List: This list focuses on smart contracts deployed on the Ethereum blockchain. It provides information about the contract address, ABI (application binary interface), and other relevant contract details.
- Addresses List: This list includes Ethereum addresses associated with specific entities or projects. It includes addresses of known wallets, exchanges, dApps (decentralized applications), and other relevant Ethereum participants.
- ENS (Ethereum name service) List: ENS is a decentralized domain name system built on the Ethereum blockchain. This list contains ENS domain names and their corresponding Ethereum addresses.
- Airdrops List: Airdrops refers to the distribution of free tokens to the Ethereum community. This list provides information about past and upcoming airdrops, including details about the airdrop project, token, and distribution methods.
- ENS Reverse Resolution List: This list is a reverse lookup for ENS domain names. It maps Ethereum addresses back to their corresponding ENS domains.
3.2. Proposed Framework
3.3. Word Embedding
3.4. Deep Convolutional Neural Networks
3.4.1. Long Short-Term Memory (LSTM)
3.4.2. Bi-Directional Long Short-Term Memory (Bi-LSTM)
3.4.3. CNN-LSTM
3.5. Parameter Settings
3.6. Ensemble Voting
Algorithm 1. Ensemble stacking algorithm. Ensemble learning algorithm |
Input: Training dataset , base learners , meta-learner . |
Output: Ensemble model predictions. |
Stage 1: Construct an ensemble of base models:
|
Stage 2: Train the ensemble:
|
Stage 3: Test the meta-learner on new data:
|
3.7. Performance Evaluation
4. Experimental Results
4.1. Implementation and Dataset
4.2. Results
4.3. Comparison with Existing Methodologies
- The blacklist-based approach involves maintaining a blacklist of known phishing addresses or patterns. Phishing addresses or patterns are added to the blacklist based on historical data or user reports. When a new transaction occurs, it is checked against the blacklist, and if a match is found, the transaction is flagged as potentially malicious. However, this approach relies on the availability and accuracy of the blacklist, which can be challenging to maintain and may not cover all possible phishing attempts.
- The heuristics-based approach utilizes predefined heuristics or rules to identify potential phishing transactions. These heuristics can include unusual transaction patterns, high gas fees, suspicious addresses, or known phishing indicators. Phishing attempts are flagged based on the violation of these heuristics. While heuristics can be effective in detecting some phishing attempts, they may also generate false positives or miss new and evolving phishing techniques.
- The machine-learning (ML)-based approaches leverage algorithms and models trained on historical data to detect phishing attempts. Features such as transaction patterns, transaction metadata, address reputation, and network behavior are extracted, and ML models are trained to classify transactions as phishing or legitimate. ML models, such as decision trees, random forests, or neural networks, can make predictions based on these features. ML-based approaches have the advantage of adapting to new phishing techniques by continuously retraining the models. However, they require a significant amount of labeled training data and may have difficulty handling adversarial attacks aimed at bypassing the detection models.
- The consensus-based approach involves utilizing the consensus mechanism of the blockchain network to detect phishing attempts. By analyzing the behavior of nodes in the network and comparing their transaction validation results, discrepancies or suspicious behavior can be identified. Nodes that consistently provide incorrect validation results or exhibit malicious behavior can be flagged as potential phishing nodes. This approach relies on the assumption that a majority of the network nodes are honest and can be challenging to implement in networks with a low number of participating nodes.
- Ensemble learning can be applied by combining multiple machine learning models, such as decision trees, random forests, or gradient-boosting algorithms. Each model in the ensemble is trained on different subsets of the data or with different feature representations. The outputs of individual models are combined, either through majority voting or weighted averaging, to make the final prediction. Ensemble learning can improve detection accuracy by leveraging the strengths of different models and reducing the impact of individual model weaknesses. It can also help mitigate false positives and false negatives, leading to more reliable phishing detection in blockchain transaction networks.
- Ensemble learning can also be applied by combining different methodologies discussed earlier, such as combining blacklisting, heuristics, and machine learning-based approaches. Each methodology can contribute unique strengths to the ensemble, leading to a more comprehensive and robust phishing detection system. For example, the outputs of blacklisting, heuristics, and machine learning models can be combined using ensemble techniques to make the final decision. This approach helps leverage the complementary nature of different methodologies and enhance the overall accuracy and effectiveness of phishing detection.
- Ensemble learning can be made adaptive by continuously monitoring the performance of individual models or methodologies and dynamically adjusting their contributions to the ensemble. This adaptability allows the system to respond to changes in the phishing landscape and quickly incorporate new detection techniques or update existing models. By combining ensemble learning with adaptive mechanisms, the phishing detection system can stay updated with evolving phishing techniques and improve its resilience against emerging threats in blockchain transaction networks.
4.4. Comparison with Existing Studies
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Malla, T.B.; Bhattarai, A.; Parajuli, A.; Shrestha, A.; Chhetri, B.B.; Chapagain, K. Status, Challenges and Future Directions of Blockchain Technology in Power System: A State of Art Review. Energies 2022, 15, 8571. [Google Scholar] [CrossRef]
- Ogundokun, R.O.; Misra, S.; Maskeliunas, R.; Damasevicius, R. A review on federated learning and machine learning approaches: Categorization, application areas, and blockchain technology. Information 2022, 13, 263. [Google Scholar] [CrossRef]
- Ogundokun, R.O.; Arowolo, M.O.; Misra, S.; Damasevicius, R. An efficient blockchain-based IoT system using improved KNN machine learning classifier. In Blockchain Based Internet of Things; De, D., Bhattacharyya, S., Rodrigues, J.J.P.C., Eds.; Lecture Notes on Data Engineering and Communications Technologies; Springer: Singapore, 2022; Volume 112. [Google Scholar] [CrossRef]
- Aslan, B.; Ataşen, K. COVID-19 information sharing with blockchain. Inf. Technol. Control. 2021, 50, 674–685. [Google Scholar] [CrossRef]
- Omohundro, S. Cryptocurrencies, smart contracts, and artificial intelligence. AI Matters 2014, 1, 19–21. [Google Scholar] [CrossRef]
- Li, Y. Emerging blockchain-based applications and techniques. Serv. Oriented Comput. Appl. 2019, 13, 279–285. [Google Scholar] [CrossRef]
- Sun, J.; Yan, J. Blockchain-Based sharing services: What blockchain technology can contribute to smart cities. Financ. Innov. 2016, 2, 26. [Google Scholar] [CrossRef]
- Dorri, A.; Kanhere, S.S.; Jurdak, R. Towards an Optimized BlockChain for IoT. In Proceedings of the Second International Conference on Internet-of-Things Design and Implementation (IoTDI’17), Pittsburgh, PA, USA, 18–21 April 2017; ACM: New York, NY, USA, 2017; pp. 173–178. [Google Scholar] [CrossRef]
- Dorri, A.; Kanhere, S.S.; Jurdak, R.; Gauravaram, P. Blockchain for IoT Security and Privacy: The Case Study of a Smart Home. In Proceedings of the IEEE Percom Workshop on Security Privacy and Trust in the Internet of Things, Kona, HI, USA, 13–17 March 2017. [Google Scholar]
- Wenting, L.; Alessandro Sforzin, A.; Fedorov, S.; Karame, G.O. Towards Scalable and Private Industrial Blockchains. In Proceedings of the ACM Workshop on Blockchain, Cryptocurrencies, and Contracts (BCC’17), Abu Dhabi, UAE, 2 April 2017; ACM: New York, NY, USA, 2017; pp. 9–14. [Google Scholar] [CrossRef]
- Yuan, Y.; Wang, F.Y. Towards blockchain-based intelligent transportation systems. In Proceedings of the 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), Rio de Janeiro, Brazil, 1–4 November 2016; pp. 2663–2668. [Google Scholar] [CrossRef]
- Sharma, P.K.; Moon, S.Y.; Park, J.H. Block-VN: A distributed blockchain-based vehicular network architecture in smart City. J. Inf. Process. Syst. 2017, 13. [Google Scholar] [CrossRef]
- Svetinovic, D. Blockchain Engineering for the Internet of Things: Systems Security Perspective. In Proceedings of the 3rd ACM International Workshop on IoT Privacy, Trust, and Security (IoTPTS’17), Abu Dhabi, UAE, 2 April 2017; ACM: New York, NY, USA, 2017; p. 1. [Google Scholar] [CrossRef]
- Sharma, P.K.; Singh, S.; Jeong, Y.S.; Park, J.H. Distblocknet: A distributed blockchain-based secure sdn architecture for IoT networks. IEEE Commun. Mag. 2017, 55, 78–85. [Google Scholar] [CrossRef]
- Luu, L.; Chu, D.H.; Olickel, H.; Saxena, P.; Hobor, A. Making Smart Contracts Smarter. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (CCS’16), Vienna, Austria, 24–26 October 2016; ACM: New York, NY, USA, 2016; pp. 254–269. [Google Scholar] [CrossRef]
- Wangsaputra, N.; Catur Candra, M.Z. Cadfort: A Decentralized Internet of Things Platform Based on Kademlia. In Proceedings of the 2018 5th International Conference on Data and Software Engineering (ICoDSE), Mataram, Indonesia, 7–8 November 2018. [Google Scholar] [CrossRef]
- Nguyen, Q.K. Blockchain—A Financial Technology for Future Sustainable Development. In Proceedings of the 2016 3rd International Conference on Green Technology and Sustainable Development (GTSD), Kaohsiung, Taiwan, 24–25 November 2016; pp. 51–54. [Google Scholar] [CrossRef]
- Asharaf, S.; Adarsh, S. Decentralized Computing Using Blockchain Technologies and Smart Contracts: Emerging Research and Opportunities; IGI Global: Hershey, PA, USA, 2017. [Google Scholar]
- Weking, J.; Mandalenakis, M.; Hein, A.; Hermes, S.; Böhm, M.; Krcmar, H. The impact of blockchain technology on business models–a taxonomy and archetypal patterns. Electron. Mark. 2019, 30, 285–305. [Google Scholar] [CrossRef]
- Treiblmaier, H.; Rejeb, A.; Strebinger, A. Blockchain as a Driver for Smart City Development: Application Fields and a Comprehensive Research Agenda. Smart Cities 2020, 3, 853–872. [Google Scholar] [CrossRef]
- Xu, L.; Shah, N.; Chen, L.; Diallo, N.; Gao, Z.; Lu, Y.; Shi, W. Enabling the Sharing Economy: Privacy Respecting Contract based on Public Blockchain. In Proceedings of the ACM Workshop on Blockchain, Cryptocurrencies and Contracts (BCC’17), Abu Dhabi, UAE, 2 April 2017; ACM: New York, NY, USA, 2017; pp. 15–21. [Google Scholar] [CrossRef]
- Gori, P.; Parcu, P.L.; Stasi, M.L. Smart Cities and Sharing Economy, Vol 96, Robert Schuman Centre for Advanced Studies Research Paper No; RSCAS. European University Institute: Fiesole, Italy, 2015. [Google Scholar]
- Zutshi, A.; Grilo, A.; Nodehi, T. The value proposition of blockchain technologies and its impact on Digital Platforms. Comput. Ind. Eng. 2021, 155, 107187. [Google Scholar] [CrossRef]
- Karunakaran, A.; Divakaran, P. Decentralized blockchain data storage using artificial intelligence. Our Heritage. In Proceedings of the GRCF Dubai International Conference on Sustainability and Innovation in Higher Education, Engineering Technology, Science, Management and Humanities, Dubai, UAE, 23–24 November; 2019; Volume 67, pp. 8–13. [Google Scholar]
- Lavanga, M.; Drosner, M. Towards a New Paradigm of the Creative City or the Same Devil in Disguise? Culture-led Urban (Re)development and Sustainability. In Cultural Industries and the Environmental Crisis; Oakley, K., Banks, M., Eds.; Springer: Cham, Switzerland, 2020. [Google Scholar] [CrossRef]
- Rubino, S.C.; Hazenberg, W.; Huisman, M. Meta Products: A Meaningful Design for Our Connected World; BIS Publishers: Amsterdam, The Netherlands, 2011. [Google Scholar]
- Putra, G.D.; Dedeoglu, V.; Kanhere, S.S.; Jurdak, R. Trust management in decentralized IoT access control system. In Proceedings of the 2020 IEEE International Conference on Blockchain and Cryptocurrency (ICBC), Toronto, ON, Canada, 3–6 May 2020; pp. 1–9. [Google Scholar]
- Malik, S.; Dedeoglu, V.; Kanhere, S.S.; Jurdak, R. Trustchain: Trust management in blockchain and IoT supported supply chains. In Proceedings of the 2019 IEEE International Conference on Blockchain, Atlanta, GA, USA, 14–17 July 2019; pp. 184–193. [Google Scholar]
- Zhang, R.; Xue, R.; Liu, L. Security, and Privacy on Blockchain. ACM Comput. Surv. 2019, 52, 1–34. [Google Scholar] [CrossRef]
- Crosby, M.; Pattanayak, P.; Verma, S.; Kalyanaraman, V. Blockchain technology: Beyond bitcoin. Appl. Innov. 2016, 2, 6–10. [Google Scholar]
- Shrestha, A.K.; Vassileva, J.; Deters, R. A Blockchain Platform for User Data Sharing Ensuring User Control and Incentives. Front. Blockchain 2020, 3, 497985. [Google Scholar] [CrossRef]
- An, Y.; Liu, Y.; Zeng, J.; Du, H.; Zhang, J.; Zhao, J. Trusted collection, management, and sharing of data based on blockchain and IoT devices. In Proceedings of the 2019 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI), Zhengzhou, China, 6–8 November 2019; pp. 27–32. [Google Scholar]
- Ramachandran, A.; Kantarcioglu, M. Smartprovenance: A distributed, blockchain-based data provenance system. In Proceedings of the Eighth ACM Conference on Data and Application Security and Privacy, Tempe, AZ, USA, 19–21 March 2018; pp. 35–42. [Google Scholar]
- Wang, S.; Zhang, Y.; Zhang, Y. A blockchain-based framework for data sharing with fine-grained access control in decentralized storage systems. IEEE Access 2018, 6, 38437–38450. [Google Scholar] [CrossRef]
- Saad, M.; Spaulding, J.; Njilla, L.; Kamhoua, C.A.; Nyang, D.; Mohaisen, A. Overview of Attack Surfaces in Blockchain. In Blockchain for Distributed Systems Security; Wiley: Hoboken, NJ, USA, 2019; pp. 51–66. [Google Scholar] [CrossRef]
- Saad, M.; Spaulding, J.; Njilla, L.; Kamhoua, C.; Shetty, S.; Nyang, D.; Mohaisen, D. Exploring the Attack Surface of Blockchain: A Comprehensive Survey. IEEE Commun. Surv. Tutor. 2020, 22, 1977–2008. [Google Scholar] [CrossRef]
- Glaser, F. Pervasive Decentralisation of Digital Infrastructures: A Framework for Blockchain-enabled System and Use Case Analysis. In Proceedings of the 50th Hawaii International Conference on System Sciences, HICSS 2017, Hilton Waikoloa Village, HI, USA, 4–7 January 2017. [Google Scholar]
- Voskobojnikov, A.; Skwarek, V.; Mashatan, A.; Matsuo, S.; Rowell, C.; Weingärtner, T. Balancing Security: A Moving Target. In Building Decentralized Trust; Lemieux, V.L., Feng, C., Eds.; Springer: Cham, Switzerland, 2021. [Google Scholar] [CrossRef]
- Dorri, A.; Roulin, C.; Jurdak, R.; Kanhere, S.S. On the activity privacy of blockchain for IoT. In Proceedings of the 2019 IEEE 44th Conference on Local Computer Networks (LCN), Osnabrueck, Germany, 14–17 October 2019; pp. 258–261. [Google Scholar]
- Zhao, Y.; Zhao, J.; Jiang, L.; Tan, R.; Niyato, D.; Li, Z.; Liu, Y. Privacy-preserving blockchain-based federated learning for IoT devices. IEEE Internet Things J. 2020, 8, 1817–1829. [Google Scholar] [CrossRef]
- Chiew, K.L.; Yong, K.S.C.; Tan, C.L. A survey of phishing attacks: Their types, vectors and technical approaches. Expert Syst. Appl. 2018, 106, 1–20. [Google Scholar] [CrossRef]
- Basit, A.; Zafar, M.; Liu, X.; Javed, A.R.; Jalil, Z.; Kifayat, K. A comprehensive survey of AI-enabled phishing attacks detection techniques. Telecommun. Syst. 2021, 76, 139–154. [Google Scholar] [CrossRef]
- Jain, A.K.; Gupta, B.B. A survey of phishing attack techniques, defense mechanisms, and open research challenges. Enterp. Inf. Syst. 2021, 16, 527–565. [Google Scholar] [CrossRef]
- Khonji, M.; Iraqi, Y.; Jones, A. Phishing detection: A literature survey. IEEE Commun. Surv. Tutor. 2013, 15, 2091–2121. [Google Scholar] [CrossRef]
- Azeez, N.A.; Salaudeen, B.B.; Misra, S.; Damaševičius, R.; Maskeliūnas, R. Identifying phishing attacks in communication networks using URL consistency features. Int. J. Electron. Secur. Digit. Forensics 2020, 12, 200–213. [Google Scholar] [CrossRef]
- Andryukhin, A.A.; Phishing, A. Preventions in Blockchain-Based Projects. In Proceedings of the International Conference on Engineering Technologies and Computer Science (EnT), Moscow, Russia, 26–27 March 2019. [Google Scholar] [CrossRef]
- Alharbi, A.; Alosaimi, W.; Alyami, H.; Rauf, H.T.; Damaševičius, R. Botnet attack detection using local-global best bat algorithm for the industrial internet of things. Electronics 2021, 10, 1341. [Google Scholar] [CrossRef]
- Toldinas, J.; Venčkauskas, A.; Damaševičius, R.; Grigaliūnas, Š.; Morkevičius, N.; Baranauskas, E. A novel approach for network intrusion detection using multistage deep learning image recognition. Electronics 2021, 10, 1854. [Google Scholar] [CrossRef]
- Nisa, M.; Shah, J.H.; Kanwal, S.; Raza, M.; Khan, M.A.; Damaševičius, R.; Blažauskas, T. Hybrid malware classification method using segmentation-based fractal texture analysis and deep convolution neural network features. Appl. Sci. 2020, 10, 4966. [Google Scholar] [CrossRef]
- Hemalatha, J.; Roseline, S.A.; Geetha, S.; Kadry, S.; Damaševičius, R. An efficient densenet-based deep learning model for malware detection. Entropy 2021, 23, 344. [Google Scholar] [CrossRef]
- Awan, M.J.; Masood, O.A.; Mohammed, M.A.; Yasin, A.; Zain, A.M.; Damaševičius, R.; Abdulkareem, K.H. Image-based malware classification using vgg19 network and spatial convolutional attention. Electronics 2021, 10, 2444. [Google Scholar] [CrossRef]
- Yong, B.; Wei, W.; Li, K.; Shen, J.; Zhou, Q.; Wozniak, M.; Damaševičius, R. Ensemble machine learning approaches for web shell detection in the internet of things environments. Trans. Emerg. Telecommun. Technol. 2020, 33, e4085. [Google Scholar] [CrossRef]
- Damaševičius, R.; Venčkauskas, A.; Toldinas, J.; Grigaliūnas, Š. Ensemble-based classification using neural networks and machine learning models for windows pe malware detection. Electronics 2021, 10, 485. [Google Scholar] [CrossRef]
- Azeez, N.A.; Odufuwa, O.E.; Misra, S.; Oluranti, J.; Damaševičius, R. Windows PE malware detection using ensemble learning. Informatics 2021, 8, 10. [Google Scholar] [CrossRef]
- Awotunde, J.B.; Ogundokun, R.O.; Misra, S.; Adeniyi, E.A.; Sharma, M.M. Blockchain-Based Framework for Secure Transaction in Mobile Banking Platform. Adv. Intell. Syst. Comput. 2021, 1375, 525–534. [Google Scholar]
- Buterin, V. A next-generation smart contract, and decentralized application platform. White Pap. 2014, 3, 37. [Google Scholar]
- Eskandari, S.; Clark, J.; Barrera, D.; Stobert, E. A first look at the usability of bitcoin key management. arXiv 2018, arXiv:1802.04351. [Google Scholar]
- Sheng, S.; Broderick, L.; Koranda, C.A.; Hyland, J.J. Why Johnny Still Can’t Encrypt: Evaluating the Usability of Email Encryption Software. Available online: https://cups.cs.cmu.edu/soups/2006/posters/shengposter_abstract.pdf (accessed on 25 December 2019).
- Gaw, S.; Felten, E.W.; Fernandez-Kelly, P. Secrecy, flagging, and paranoia: Adoption criteria in an encrypted email. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, Montréal, QC, Canada, 22–27 April 2006; pp. 591–600. [Google Scholar]
- Schultz, E.E.; Proctor, R.W.; Lien, M.C.; Salvendy, G. Usability and security an appraisal of usability issues in information security methods. Comput. Secure. 2001, 20, 620–634. [Google Scholar] [CrossRef]
- Garfinkel, S.L.; Margrave, D.; Schiller, J.I.; Nordlander, E.; Miller, R.C. How to make secure email easier to use. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, Portland, OR, USA, 2–7 April 2005; pp. 701–710. [Google Scholar]
- Ruoti, S.; Seamons, K. Johnny’s Journey Toward Usable Secure Email. IEEE Secure. Priv. 2019, 17, 72–76. [Google Scholar] [CrossRef]
- Pham, T.; Lee, S. Anomaly detection in bitcoin network using unsupervised learning methods. arXiv 2016, arXiv:1611.03941. [Google Scholar]
- Do, H.G.; Ng, W.K. Blockchain-based system for secure data storage with private keyword search. In Proceedings of the 2017 IEEE World Congress on Services (SERVICES), Honolulu, HI, USA, 25–30 June 2017; pp. 90–93. [Google Scholar]
- Devi, K.; Paulraj, D.; Muthusenthil, B. Deep Learning Based Security Model for Cloud based Task Scheduling. KSII Trans. Internet Inf. Syst. 2020, 14, 3663–3679. [Google Scholar] [CrossRef]
- Sermakani, A.M.; Paulraj, D. Effective Data Storage and Dynamic Data Auditing Scheme for Providing Distributed Services in Federated Cloud. J. Circuits Syst. Comput. 2020, 29, 2050259. [Google Scholar] [CrossRef]
- Hariharan, B.; Paul Raj, D. WBAT Job Scheduler: A Multi-Objective Approach for Job Scheduling Problem on Cloud Computing. J. Circuits Syst. Comput. 2019, 29, 2050089. [Google Scholar] [CrossRef]
- Perard, D.; Gicquel, L.; Lacan, J. BlockHouse: Blockchain-based Distributed Storehouse System. In Proceedings of the 2019 9th Latin-American Symposium on Dependable Computing (LADC), Natal, Brazil, 19–21 November 2019; pp. 1–4. [Google Scholar]
- Michelin, R.A.; Dorri, A.; Steger, M.; Lunardi, R.C.; Kanhere, S.S.; Jurdak, R.; Zorzo, A.F. SpeedyChain: A framework for decoupling data from the blockchain for smart cities. In Proceedings of the 15th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking, and Services, New York, NY, USA, 5–7 November 2018; pp. 145–154. [Google Scholar]
- Hossain, E.; Khan, I.; Un-Noor, F.; Sikander, S.S.; Sunny, M.S.H. Application of big data and machine learning in smart grid, and associated security concerns: A review. IEEE Access 2019, 7, 13960–13988. [Google Scholar] [CrossRef]
- Anthi, E.; Williams, L.; Słowińska, M.; Theodorakopoulos, G.; Burnap, P. A supervised intrusion detection system for smart home IoT devices. IEEE Internet Things J. 2019, 6, 9042–9053. [Google Scholar] [CrossRef]
- Wei, L.; Luo, W.; Weng, J.; Zhong, Y.; Zhang, X.; Yan, Z. Machine learning-based malicious application detection of android. IEEE Access 2017, 5, 25591–25601. [Google Scholar] [CrossRef]
- Restuccia, F.; D’Oro, S.; Melodia, T. Securing the internet of things in the age of machine learning and software-defined networking. IEEE Internet Things J. 2018, 5, 4829–4842. [Google Scholar] [CrossRef]
- Mahdavinejad, M.S.; Rezvan, M.; Barekatain, M.; Adibi, P.; Barnaghi, P.; Sheth, A.P. Machine learning for Internet of Things data analysis: A survey. Digit. Commun. Netw. 2018, 4, 161–175. [Google Scholar] [CrossRef]
- Kumar, N.; Singh, A.; Handa, A.; Shukla, S.K. Detecting Malicious Accounts on the Ethereum Blockchain with Supervised Learning. In Proceedings of the International Symposium on Cyber Security Cryptography and Machine Learning, Be’er Sheva, Israel, 8–9 July 2020; pp. 94–109. [Google Scholar]
- Dalal, H.; Abulaish, M. A multilayer perceptron architecture for detecting deceptive cryptocurrencies in coin market capitalization data. In Proceedings of the 2019 IEEE/WIC/ACM International Conference on Web Intelligence, Thessaloniki, Greece, 14–17 October 2019; pp. 438–442. [Google Scholar]
- Yuan, Z.; Yuan, Q.; Wu, J. Phishing Detection on Ethereum via Learning Representation of Transaction Subgraphs. In Proceedings of the International Conference on Blockchain and Trustworthy Systems, Dali, China, 6–7 August 2020; pp. 178–191. [Google Scholar]
- Chen, L.; Peng, J.; Liu, Y.; Li, J.; Xie, F.; Zheng, Z. Phishing Scams Detection in Ethereum Transaction Network. ACM Trans. Internet Technol. 2021, 21, 1–16. [Google Scholar] [CrossRef]
- Chen, W.; Zheng, Z.; Ngai, E.C.H.; Zheng, P.; Zhou, Y. Exploiting Blockchain Data to Detect Smart Ponzi Schemes on Ethereum. IEEE Access 2019, 7, 37575–37586. [Google Scholar] [CrossRef]
- Chen, W.; Zheng, Z.; Cui, J.; Ngai, E.; Zheng, P.; Zhou, Y. Detecting Ponzi schemes on ethereum: Towards healthier blockchain technology. In Proceedings of the 2018 World Wide Web Conference, Lyon, France, 23–27 April 2018. [Google Scholar]
- GitHub—MyEtherWallet/Ethereum-Lists: A Repository for Maintaining Lists of Things Like Malicious URLs, Fake Token Addresses, and so Forth. Available online: https://github.com/MyEtherWallet/ethereum-lists (accessed on 1 February 2023).
Parameter | Value |
---|---|
Num of filters (CNN) | 16 |
Filter length (CNN) | 5 |
Max Sequence Length | 32 |
Batch size | 64 |
Epochs | 100 |
Loss | Binary cross entropy |
Optimizer | nAdam |
Activation unit | ReLU -Rectified linear units |
Dropout | 0.2 |
LR patience | 5 |
Parameters | Tested Values | Bi-LSTM |
---|---|---|
Input features | 16, 32, 64 | 32 |
Hidden size | 32, 64, 128, 256 | 64 |
Number of layers | 2, 3, 4 | 3 |
Batch size | 16, 32, 64 | 32 |
Dropout | 0.2, 0.3, 0.4, 0.5, 0.6, 0.7 | 0.3 |
Learning rate | 0.00001, 0.0001, 0.001 | 0.0001 |
Optimizer | Adam, nAdam, SGD | Adam |
Model | Parameter Values |
---|---|
LSTM | Hidden layers = 128 Dropout = 0.3 Recurrent dropout = 0.3 |
Bidirectional LSTM | Hidden layers = 128 Dropout = 0.3 Recurrent dropout = 0.3 |
CNN + LSTM | Number of convolution filters = 512 Kernel size = 3 Activation function = RELU Hidden layers = 128 Dropout = 0.3 Recurrent dropout = 0.3 |
Classifiers | TP | TN | FP | FN |
---|---|---|---|---|
Bi-LSTM | 712 | 0 | 9 | 0 |
CNN-LSTM | 711 | 8 | 1 | 1 |
Embedding LSTM | 707 | 8 | 1 | 5 |
Classifier | Accuracy | Sensitivity (Recall) | Precision | F-Score |
---|---|---|---|---|
Embedding LSTM | 98.75% | 100% | 98.75% | 99.37% |
CNN-LSTM | 98.75% | 99.86% | 98.89% | 99.37% |
Bi-LSTM | 99.17% | 99.86% | 99.30% | 99.58% |
Ensemble | 99.72% | 99.86% | 99.86% | 99.86% |
References | Method | Scam | Accuracy | Recall | Precision | F-Score |
---|---|---|---|---|---|---|
[75] | XGBoost | Malicious users’ detection | 96.54% | ----- | ------ | ----- |
[76] | Multilayer perception | Cryptocurrency deception | 98.00% | ------ | 98.98% | ------ |
[77] | Graph2Vec | Phishing | ----- | 77.00% | 69.00% | 73.00% |
[78] | GCN | Phishing | ------- | 14.53% | 72.94% | 23.57% |
Proposed method | Ensemble | Phishing | 99.72% | 99.86% | 99.86% | 99.86% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ogundokun, R.O.; Arowolo, M.O.; Damaševičius, R.; Misra, S. Phishing Detection in Blockchain Transaction Networks Using Ensemble Learning. Telecom 2023, 4, 279-297. https://doi.org/10.3390/telecom4020017
Ogundokun RO, Arowolo MO, Damaševičius R, Misra S. Phishing Detection in Blockchain Transaction Networks Using Ensemble Learning. Telecom. 2023; 4(2):279-297. https://doi.org/10.3390/telecom4020017
Chicago/Turabian StyleOgundokun, Roseline Oluwaseun, Micheal Olaolu Arowolo, Robertas Damaševičius, and Sanjay Misra. 2023. "Phishing Detection in Blockchain Transaction Networks Using Ensemble Learning" Telecom 4, no. 2: 279-297. https://doi.org/10.3390/telecom4020017