Loading...
|
Please use this identifier to cite or link to this item:
https://nccur.lib.nccu.edu.tw/handle/140.119/152038
|
| Title: | 基於區塊鏈的郵件系統與 AI 信任評估
Blockchain-based Email System with AI Trust Evaluation |
| Authors: | 張義猷
Chang, Daniel |
| Contributors: | 謝佩璇
Hsieh, Pei-Hsuan
張義猷
Chang, Daniel |
| Keywords: | 區塊鏈
智能合約
人工智慧
監督式學習
隱私保護
Blockchain
Smart contracts
Artificial Intelligence
Supervised learning
Privacy protection |
| Date: | 2024 |
| Issue Date: | 2024-07-01 12:30:49 (UTC+8) |
| Abstract: | 在數位時代，詐騙者利用各種方式進入我們的信箱，企圖詐騙個人資訊、財務資訊或金錢。區塊鏈是一種分散式數據庫技術，可以在各個領域應用。區塊鏈的核心特點是去中心化和不可竄改性，確保數據的安全和透明。在郵件管理方面，區塊鏈確保郵件的安全和不可竄改性，防止詐騙和數據外洩。通過將郵件數據記錄在不同節點上，區塊鏈確保了郵件的來源和完整性。智能合約可實現自動加密和解密，增強了隱私保護。此技術還有助於郵件跟蹤和驗證，提高了交流的可追溯性。本研究先開發基於區塊鏈之郵件系統，再整合智能合約，採用 11 種 AI 模型評估，結果 Naive Bayes 模型的訓練結果分數最佳，因此將此演算法嵌入智能合約中，有利於將先前訓練的模型進行預測。開發的郵件系統整體架構包括鏈外和鏈上組件，其中鏈外組件涉及數據和訓練階段，用於對數據進行預處理和特徵提取。一旦訓練階段完
成，模型可以在智能合約中準備好，用於進行預測，藉著此 AI 技術的加入增強了智能合約的功能，本研究提出的此方式能有效判讀郵件是否為垃圾信件，更能有效地檢測郵件內容的真實性。
In the digital era, fraudsters employ various means to infiltrate our email inboxes, attempting to deceive individuals into divulging personal information, financial details, or money. Blockchain is a decentralized database technology that finds applications across various domains. The core features of blockchain are decentralization and immutability, ensuring the security and transparency of data. In email management, blockchain ensures the security and tamper resistance of emails, preventing fraud and data leaks. By recording email data across different nodes, blockchain ensures the origin and integrity of emails. Smart contracts enable automatic encryption and decryption, enhancing privacy protection. This technology also aids in email tracking and verification, improving the traceability of communication. This research first develops a blockchain-based email system and then integrates smart contracts, employing 11 AI models for evaluation, with the Naive Bayes
model yielding the best training results. Therefore, embedding this algorithm into smart contracts facilitates predictive analysis based on previously trained models. The overall architecture of the developed email system includes off-chain and on-chain components, with off-chain components involving data and training phases for preprocessing and feature extraction. Once the training phase is completed, the model can be prepared within the smart contract
for predictive analysis. By incorporating this AI technology, the functionality of smart contracts is enhanced. This study proposes an effective method for
determining whether an email is spam and efficiently detecting the authentic-
ity of email content. |
| Reference: | [1] AWS Blockchain. https://aws.amazon.com/tw/what-is/blockchain/
?aws-products-all.sort-by=item.additionalFields.productNameLowercase&
aws-products-all.sort-order=asc. Accessed: 2024-03-13.
[2] CSOSocialEngineering. https://www.csoonline.com/article/571993/
social-engineering-definition-examples-and-techniques.html. Accessed:
2022-02-7.
[3] SocialEngineeringDefinition. https://www.cisco.com/c/en/us/products/
security/what-is-social-engineering.html.
[4] Nazmiye Ceren Abay, Cuneyt Gurcan Akcora, Yulia R Gel, Murat Kantarcioglu,
Umar D Islambekov, Yahui Tian, and Bhavani Thuraisingham. Chainnet: Learning
on blockchain graphs with topological features. In 2019 IEEE international confer-
ence on data mining (ICDM), pages 946–951. IEEE, 2019.
[5] Cuneyt Gurcan Akcora, Yulia R Gel, and Murat Kantarcioglu. Blockchain: A graph
primer. arXiv preprint arXiv:1708.08749, 2017.
[6] Rasim Alguliyev and Saadat Nazirova. Two approaches on implementation of cbr
and crm technologies to the spam filtering problem. 2011.
[7] Tae-Ki An and Moon-Hyun Kim. A new diverse adaboost classifier. In 2010 International conference on artificial intelligence and computational intelligence, volume 1,
pages 359–363. IEEE, 2010.
[8] A Arnold. Promising use cases of blockchain in cybersecurity. Forbes, ed.(Forbes,
Jersey City, 2019), 4.
[9] Diana Baby, Sujitha Juliet Devaraj, Jude Hemanth, et al. Leukocyte classification
based on feature selection using extra trees classifier: Atransfer learning approach.
Turkish Journal of Electrical Engineering and Computer Sciences, 29(8):2742–
2757, 2021.
[10] Mahmoud Bassiouni, M Ali, and EA El-Dahshan. Ham and spam e-mails classi-
fication using machine learning techniques. Journal of Applied Security Research,
13(3):315–331, 2018.
[11] Alexy Bhowmick and Shyamanta M Hazarika. Machine learning for e-mail spam
filtering: review, techniques and trends. arXiv preprint arXiv:1606.01042, 2016.
[12] Hanif Bhuiyan, Akm Ashiquzzaman, Tamanna Islam Juthi, Suzit Biswas, and Jinat
Ara. A survey of existing e-mail spam filtering methods considering machine learn-
ing techniques. Global Journal of Computer Science and Technology, 18(2):20–29,
2018.
[13] Enrico Blanzieri and Anton Bryl. E-mail spam filtering with local svm classifiers.
2008.
[14] Enrico Blanzieri and Anton Bryl. A survey of learning-based techniques of email
spam filtering. Artificial Intelligence Review, 29:63–92, 2008.
[15] Guang Chen, Bing Xu, Manli Lu, and Nian-Shing Chen. Exploring blockchain technology and its potential applications for education. Smart Learning Environments,
5(1):1–10, 2018.
[16] Sudeep Choudhari and Suman Das. Spam e-mail identification using blockchain
technology. In 2021 International Conference on Communication, Control and In-
formation Sciences (ICCISc), volume 1, pages 1–5, 2021.
[17] Stefano Cresci, Marinella Petrocchi, Angelo Spognardi, and Stefano Tognazzi. On
the capability of evolved spambots to evade detection via genetic engineering. Online
Social Networks and Media, 9:1–16, 2019.
[18] Nikolina Cveticanin. What’s on the other side of your inbox –20 spam statistics
for 2023, July 14, 2023.
[19] Mohamed Amine Ferrag, Leandros Maglaras, Sotiris Moschoyiannis, and Helge Jan-
icke. Deep learning for cyber security intrusion detection: Approaches, datasets, and
comparative study. Journal of Information Security and Applications, 50:102419,
2020.
[20] Wilfried N Gansterer, Andreas GK Janecek, and Robert Neumayer. Spam filtering
based on latent semantic indexing. Survey of Text Mining II: Clustering, Classifica-
tion, and Retrieval, pages 165–183, 2008.
[21] José Chamadoira González, Vicente García-Díaz, Edward Rolando Núñez-Valdez,
Alberto Gómez Gómez, and Ruben Gonzalez Crespo. Replacing email protocols
with blockchain-based smart contracts. Cluster Computing, 23:1795–1801, 2020.
[22] José González, Vicente García Díaz, Edward Núñez Valdez, Alberto Gomez, and
Ruben Gonzalez Crespo. Replacing email protocols with blockchain-based smart
contracts. Cluster Computing, IP:1–6, 09 2020.
[23] J Griffey. Blockchain & intellectual property. Internet Librarian, 2016.
[24] Sumeer Gul and Shohar Bano. Smart libraries: an emerging and innovative techno-
logical habitat of 21st century. The Electronic Library, 37(5):764–783, 2019.
[25] Kevin W Hamlen and Bhavani Thuraisingham. Data security services, solutions and
standards for outsourcing. Computer Standards & Interfaces, 35(1):1–5, 2013.
[26] Nabi Hasan. Blockchain technology and its application in libraries. Library Herald,
58(4):118–125, 2020.
[27] Matthew B Hoy. An introduction to the blockchain and its implications for libraries
and medicine. Medical reference services quarterly, 36(3):273–279, 2017.
[28] Investopedia. Blockchain, 2022.
[29] Md Khairul Islam, Prithula Hridi, Md Shohrab Hossain, and Husnu S Narman. Net-
work anomaly detection using lightgbm: A gradient boosting classifier. In 2020 30th
international telecommunication networks and applications conference (ITNAC),
pages 1–7. IEEE, 2020.
[30] Ankit Kumar Jain and Brij B Gupta. A novel approach to protect against phishing
attacks at client side using auto-updated white-list. EURASIP Journal on Information
Security, 2016:1–11, 2016.
[31] Ankit Kumar Jain and Brij B Gupta. Towards detection of phishing websites on
client-side using machine learning based approach. Telecommunication Systems,
68:687–700, 2018.
[32] Mahasak Ketcham, Thittaporn Ganokratanaa, Patiyuth Pramkeaw, and Narumol
Chumuang. Spam text detection using machine learning model. In 2023 International Technical Conference on Circuits/Systems, Computers, and Communications
(ITC-CSCC), pages 1–6, 2023.
[33] Sotiris B Kotsiantis, Ioannis Zaharakis, P Pintelas, et al. Supervised machine learn-
ing: A review of classification techniques. Emerging artificial intelligence applica-
tions in computer engineering, 160(1):3–24, 2007.
[34] Nikhil Kumar, Sanket Sonowal, et al. Email spam detection using machine learn-
ing algorithms. In 2020 Second International Conference on Inventive Research in
Computing Applications (ICIRCA), pages 108–113. IEEE, 2020.
[35] Jitendra Singh Kushwah, Atul Kumar, Subhash Patel, Rishi Soni, Amol Gawande,
and Shyam Gupta. Comparative study of regressor and classifier with decision tree
using modern tools. Materials Today: Proceedings, 56:3571–3576, 2022.
[36] Konstantinos Lampropoulos, Giorgos Georgakakos, and Sotiris Ioannidis. Using
blockchains to enable big data analysis of private information. In 2019 IEEE 24th
International Workshop on Computer Aided Modeling and Design of Communica-
tion Links and Networks (CAMAD), pages 1–6. IEEE, 2019.
[37] Daekyung Lee, Mi Jin Lee, and Beom Jun Kim. Deviation-based spam-filtering
method via stochastic approach. Europhysics Letters, 121(6):68004, 2018.
[38] Jiameng Liu, Shaoliang Peng, Chengnian Long, Lijun Wei, Yunhao Liu, and Zhihui
Tian. Blockchain for data science. In Proceedings of the 2020 The 2nd International
Conference on Blockchain Technology, pages 24–28, 2020.
[39] Yue Liu, Qinghua Lu, Shiping Chen, Qiang Qu, Hugo O’Connor, Kim-
Kwang Raymond Choo, and He Zhang. Capability-based iot access control using
blockchain. Digital Communications and Networks, 7(4):463–469, 2021.
[40] Bernard Marr. How blockchain will transform the supply chain and logistics industry.
Retrieved February, 22:2018, 2018.
[41] Jose R Mendez, Tomas R Cotos-Yanez, and David Ruano-Ordas. A new semantic-
based feature selection method for spam filtering. Applied Soft Computing, 76:89–
104, 2019.
[42] Monika, Munish Kumar, and Manish Kumar. Xgboost: 2d-object recognition using
shape descriptors and extreme gradient boosting classifier. In Computational Meth-
ods and Data Engineering: Proceedings of ICMDE 2020, Volume 1, pages 207–222.
Springer, 2021.
[43] Adetoun A Oyelude. What’s trending in blockchain technology and its potential uses
in libraries. Library Hi Tech News, 36(9):17–18, 2019.
[44] Mahesh Pal. Random forest classifier for remote sensing classification. International
journal of remote sensing, 26(1):217–222, 2005.
[45] Vishwam Jaimini Pandya. Comparing handwritten character recognition by ad-
aboostclassifier and kneighborsclassifier. In 2016 8th International Conference on
Computational Intelligence and Communication Networks (CICN), pages 271–274.
IEEE, 2016.
[46] MFNK Pathan and Vijaya Kamble. A review various techniques for content based
spam filtering. Engineering and Technology, 4, 2018.
[47] Line Nybro Petersen. The ageing body in monty python live (mostly). European
journal of cultural studies, 21(3):382–394, 2018.
[48] Abdul Jabbar Saleh, Asif Karim, Bharanidharan Shanmugam, Sami Azam, Krishnan Kannoorpatti, Mirjam Jonkman, and Friso De Boer. An intelligent spam detection
model based on artificial immune system. Information, 10(6):209, 2019.
[49] Igor Santos, Yoseba K Penya, Jaime Devesa, and Pablo G Bringas. N-grams-based
file signatures for malware detection. In International Conference on Enterprise
Information Systems, volume 1, pages 317–320. SCITEPRESS, 2009.
[50] Anubhaw Kumar Suman and Madhu Patel. An introduction to blockchain technology
and its application in libraries. Available at SSRN 4019394, 2021.
[51] Melanie Swan. Blockchain: Blueprint for a new economy. ” O’Reilly Media, Inc.”,
2015.
[52] Paul J Taylor, Tooska Dargahi, Ali Dehghantanha, Reza M Parizi, and Kim-
Kwang Raymond Choo. A systematic literature review of blockchain cyber security.
Digital Communications and Networks, 6(2):147–156, 2020.
[53] Antonio Tenorio-Fornés, Viktor Jacynycz, David Llop-Vila, Antonio Sánchez-Ruiz,
and Samer Hassan. Towards a decentralized process for scientific publication and
peer review using blockchain and ipfs. 2019.
[54] Bhavani Thuraisingham, Murat Kantarcioglu, and Latifur Khan. Integrating cyber
security and data science for social media: A position paper. In 2018 IEEE Interna-
tional Parallel and Distributed Processing Symposium Workshops (IPDPSW), pages
1163–1165. IEEE, 2018.
[55] Marcos Treviso, Ji-Ung Lee, Tianchu Ji, Betty van Aken, Qingqing Cao, Manuel R
Ciosici, Michael Hassid, Kenneth Heafield, Sara Hooker, Colin Raffel, et al. Effi-
cient methods for natural language processing: A survey. Transactions of the Asso-
ciation for Computational Linguistics, 11:826–860, 2023.
[56] Sanmeet Singh Vadhava, Suyog Dhadwe, Aditya Katkar, Shubhangi Ghorkhana, and
Jisha Tinsu. A decentralized mail using blockchain. In 2023 4th International Con-
ference for Emerging Technology (INCET), pages 1–5, 2023.
[57] Tarjani Vyas, Payal Prajapati, and Somil Gadhwal. A survey and evaluation of
supervised machine learning techniques for spam e-mail filtering. In 2015 IEEE
international conference on electrical, computer and communication technologies
(ICECCT), pages 1–7. IEEE, 2015.
[58] Mathias Wien, Heiko Schwarz, and Tobias Oelbaum. Performance analysis of svc.
IEEE Transactions on Circuits and Systems for Video Technology, 17(9):1194–1203,
2007.
[59] Raymond E Wright. Logistic regression. 1995.
[60] Dawei Xu, Fudong Wu, Liehuang Zhu, Ruiguang Li, Jiaqi Gao, and Yijie She. Bues:
A blockchain-based upgraded email system. China Communications, 19(10):250–
264, 2022.
[61] Shuo Xu, Yan Li, and Zheng Wang. Bayesian multinomial naïve bayes classi-
fier to text classification. In Advanced Multimedia and Ubiquitous Engineering:
MUE/FutureTech 2017 11, pages 347–352. Springer, 2017.
[62] Dylan Yaga, Peter Mell, Nik Roby, and Karen Scarfone. Nistir 8202 blockchain tech-
nology overview. National Institute of Standards and Technology, US Department
of Commerce, Washington, USA, 2018.
[63] Masoumeh Zareapoor, Pourya Shamsolmoali, et al. Application of credit card
fraud detection: Based on bagging ensemble classifier. Procedia computer science,
48(2015):679–685, 2015.
[64] Li Zhuang, John Dunagan, Daniel R Simon, Helen J Wang, Ivan Osipkov, and J Doug
Tygar. Characterizing botnets from email spam records. Leet, 8(1):1–9, 2008. |
| Description: | 碩士
國立政治大學
資訊科學系
111753230 |
| Source URI: | http://thesis.lib.nccu.edu.tw/record/#G0111753230 |
| Data Type: | thesis |
| Appears in Collections: | [資訊科學系] 學位論文
|
Files in This Item:
| File |
Description |
Size | Format | |
|---|
| 323001.pdf | | 2373Kb | Adobe PDF | 0 | View/Open |
|
All items in 政大典藏 are protected by copyright, with all rights reserved.
|
