International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | A Secure Blockchain–NLP Integrated System for Privacy Preserving Crime Reporting and Evidence Management |
|---|---|
| ABSTRACT | The increasing prevalence of cyber-enabled and conventional crimes has created a growing demand for secure, intelligent, and privacy-preserving digital crime reporting systems. Existing centralized complaint management platforms often suffer from limitations such as data tampering, inadequate evidence protection, lack of transparency, delayed investigations, and privacy concerns that discourage victims from reporting incidents. To address these challenges, this paper proposes a Blockchain and Natural Language Processing (NLP) Integrated Crime Reporting and Evidence Management System that enables anonymous crime reporting while ensuring secure evidence handling and transparent investigation workflows. The proposed framework employs NLP techniques for complaint preprocessing and Term Frequency–Inverse Document Frequency (TF-IDF) for feature extraction. Four supervised machine learning algorithms—Multinomial Naive Bayes, Logistic Regression, Linear Support Vector Machine (Linear SVM), and Random Forest—are evaluated to automatically predict Crime Type, Indian Penal Code (IPC) Sections, Bharatiya Nyaya Sanhita (BNS) Sections, and Risk Level from complaint descriptions. Experimental analysis identifies Multinomial Naive Bayes as the most effective classifier in terms of overall predictive performance. Additionally, Cosine Similarity is utilized to retrieve semantically similar historical complaints, assisting investigators in case analysis and decision-making. To preserve digital evidence integrity, uploaded files are protected using the SHA-256 cryptographic hashing algorithm, while blockchain smart contracts maintain immutable records of complaint metadata, evidence hashes, investigation updates, and audit trails. The proposed system further incorporates role-based access control and anonymous communication between complainants and investigating officers, enhancing privacy, accountability, and operational efficiency. By integrating machine learning, NLP, cryptographic hashing, and blockchain technology into a unified framework, the proposed solution provides a secure, transparent, and scalable platform for modern digital crime reporting and forensic evidence management. |
| AUTHOR | DR. R. SRIDEVI, SINDAM AKSHAYA Professor, Department of Computer Science Engineering, Jawaharlal Nehru Technological University, Hyderabad, Telangana, India Post-Graduate Student, Department of Computer Science Engineering, Jawaharlal Nehru Technological University, Hyderabad, Telangana, India |
| VOLUME | 186 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1407055 |
| pdf/55_A Secure Blockchain–NLP Integrated System for Privacy Preserving Crime Reporting and Evidence Management.pdf | |
| KEYWORDS | |
| References | 1. P. Chaurasia, D. Rana, R. V., and S. Srividhya, "Anonymous Crime Reporting using Blockchain and Smart Contract," 2024 4th International Conference on Pervasive Computing and Social Networking (ICPCSN), IEEE, 2024. 2. D. Ashar, M. Dwivedi, P. Patil, R. Sawant, et al., "A Blockchain-Based Anonymous Crime Reporting Platform Integrating Privacy-Preserving NLP for Enhanced Public Safety," 2025 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), 2025. 3. S. Banaeian Far and M. Rajabzadeh Asaar, "A Blockchain-Based Anonymous Reporting System with No Central Authority: Architecture and Protocol," Cyber Security and Applications, vol. 2, 2024. 4. L. Zhu, J. Zhang, C. Zhang, F. Gao, Z. Chen, and Z. Li, "Achieving Anonymous and Covert Reporting on Public Blockchain Networks," Mathematics, vol. 11, no. 7, Art. 1621, 2023. 5. S. Bird, E. Klein, and E. Loper, Natural Language Processing with Python. Sebastopol, CA, USA: O'Reilly Media, 2009. 6. J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding," Proceedings of NAACL-HLT, 2019. 7. V. Sanh, L. Debut, J. Chaumond, and T. Wolf, "DistilBERT: A Distilled Version of BERT: Smaller, Faster, Cheaper and Lighter," NeurIPS Workshop, 2019. 8. F. Pedregosa et al., "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825-2830, 2011. 9. National Institute of Standards and Technology (NIST), Secure Hash Standard (SHA-256), FIPS PUB 180-4, 2015. 10. G. Wood, "Ethereum: A Secure Decentralised Generalised Transaction Ledger," Ethereum Yellow Paper, 2014. |
