An Intelligent Blockchain Based Platform for Academic Fraud Prevention and Predictive Student Analytics Using CARTNet Model
| International Journal of Electronics and Communication Engineering |
| © 2026 by SSRG - IJECE Journal |
| Volume 13 Issue 1 |
| Year of Publication : 2026 |
| Authors : Sangeetha A.S, Shunmugan S |
10.14445/23488549/IJECE-V13I1P118
How to Cite?
Sangeetha A.S, Shunmugan S, "An Intelligent Blockchain Based Platform for Academic Fraud Prevention and Predictive Student Analytics Using CARTNet Model," SSRG International Journal of Electronics and Communication Engineering, vol. 13, no. 1, pp. 241-263, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I1P118
Abstract:
The substantial dependence on an online method for maintaining academic records has raised concerns about data quality and the possibility of credential falsification due to flaws in centralized systems, such as brute-force attacks and cyber threats. Blockchain, configured with AES-256 encryption, provides a more effective and reliable approach for certifying academic records due to its ability to distribute data in a secure, decentralized manner and its resistance to hacking. Although combining blockchain technology with predictive modelling has remained extremely difficult, this proposal provides a unique approach to business models in education by merging the developing technologies associated with Deep Learning (DL) into a framework of academic management, along with a significant amount of blockchain-based secsurity and AES-256 encrypted protection of data. The proposed solution employs a new type of classifier, Chaotic-Attentive Recurrent Transformer-Net (CARTNet), which combines self-normalizing attention mechanisms with the dynamics of chaotic attractors for predicting student performance. Python software was implemented and evaluated for its performance using various metrics, including recall, accuracy, and precision. Also used a blockchain to protect the data sent between systems, and the validation of those records is conducted using the Java platform. Using these combined technologies to help create a reliable, expandable, and smart system. The system automates the confirmation of certificates and provides precise predictions of students’ academic achievements. By providing companies and educational institutions with an accurate and validated set of data-based information for making decisions, this reduces the potential risk of fraud.
Keywords:
Certificate Verification, Blockchain, AES-256 encryption, Chaotic-Attentive Recurrent Transformer Net.
References:
[1] Guiyun Feng, Muwei Fan, and Yu Chen, “Analysis and Prediction of Students’ Academic Performance Based on Educational Data Mining,” IEEE Access vol. 10, pp. 19558-19571, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Muhammad Adnan et al., “Predicting at-Risk Students at Different Percentages of Course Length for Early Intervention Using Machine Learning Models,” IEEE Access, vol. 9, pp. 7519-7539, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Aya Nabil, Mohammed Seyam, and Ahmed Abou-Elfetouh, “Prediction of Students’ Academic Performance Based on Courses’ Grades Using Deep Neural Networks,” IEEE Access, vol. 9, pp. 140731-140746, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Arun Kumar Soma, “Enhancing Supply Chain Transparency and Integrity: A Permissioned Blockchain Framework,” 2025 International Conference on Emerging Systems and Intelligent Computing (ESIC), Bhubaneswar, India, pp. 819-826, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Arun Kumar Soma, “Hybrid RNN-GRU-LSTM Model for Accurate Detection of DDoS Attacks on IDS Dataset,” Journal of Modern Technology, vol. 2, no. 1, pp. 283-291, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[6] R. Udayakumar et al., “Deep Fraud Net: A Deep Learning Approach for Cyber Security and Financial Fraud Detection and Classification,” Journal of Internet Services and Information Security, vol. 13, no. 4, pp. 138-157, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Seong-Kyu Kim, “Blockchain Smart Contract to Prevent Forgery of Degree Certificates: Artificial Intelligence Consensus Algorithm,” Electronics, vol. 11, no. 14, pp. 1-32, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Suyel Namasudra et al., “Blockchain-Based Medical Certificate Generation and Verification for IoT-Based Healthcare Systems,” IEEE Consumer Electronics Magazine, vol. 12, no. 2, pp. 83-93, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Qiang Tang, “Towards Using Blockchain Technology to Prevent Diploma Fraud,” IEEE Access, vol. 9, pp. 168678-168688, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Qilin Zhou et al., “CrossCert: A Cross-Checking Detection Approach to Patch Robustness Certification for Deep Learning Models,” Proceedings of the ACM on Software Engineering, vol. 1, no. FSE, pp. 2725-2746, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Muhammad Nauman et al., “Guaranteeing Correctness of Machine Learning Based Decision Making at Higher Educational Institutions,” IEEE Access, vol. 9, pp. 92864-92880, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Dhruvil Shah et al., “Integrating Machine Learning and Blockchain to Develop a System to Veto the Forgeries and Provide Efficient Results in Education Sector,” Visual Computing for Industry, Biomedicine, and Art, vol. 4, pp. 1-13, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Mirna Nachouki et al., “Student Course Grade Prediction using the Random Forest Algorithm: Analysis of Predictors' Importance,” Trends in Neuroscience and Education, vol. 33, pp. 1-7, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Zaffar Ahmed Shaikh et al., “Blockchain Hyperledger with Non-Linear Machine Learning: A Novel and Secure Educational Accreditation Registration and Distributed Ledger Preservation Architecture,” Applied Sciences, vol. 12, no. 5, pp. 1-20, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Fatima Ahmed Al-azazia, and Mossa Ghurab, “ANN-LSTM: A Deep Learning Model for Early Student Performance Prediction in MOOC,” Heliyon, vol. 9, no. 4, pp. 1-16, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Rosa Leonor Ulloa Cazarez, “Accuracy Comparison between Statistical and Computational Classifiers Applied for Predicting Student Performance in Online Higher Education,” Education and Information Technologies, vol. 27, pp. 11565-11590, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Bashir Khan Yousafzai et al., “Student-Performulator: Student Academic Performance Using Hybrid Deep Neural Network,” Sustainability, vol. 13, no. 17, pp. 1-21, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[18] R. Manoj, and Sandeep Joshi, “Securing Academic Certificate Verification with Blockchain-based Algorithmic Rules,” 2023 IEEE 4th International Multidisciplinary Conference on Engineering Technology (IMCET), Beirut, Lebanon, pp. 242-247, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Rojalina Priyadarshini et al., “A Faster, Integrated, and Trusted Certificate Authentication and Issuer Validation System Based on Blockchain,” IEEE Access, vol. 13, pp. 27037-27049, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Rajesh Kumar Kaushal et al., “Hyperledger Fabric based Remote Patient Monitoring Solution and Performance Evaluation,” Peer-to-Peer Networking and Applications, vol. 18, pp. 1-17, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Wenxuan Liu et al, “Ring-Overlap: A Storage Scaling Mechanism for Hyperledger Fabric,” Applied Sciences, vol. 12, no. 19, pp. 1-17, 2022.
[CrossRef] [Google Scholar] [Publisher Link]