Keywords:-
Article Content:-
Abstract
The exponential proliferation of digital data within organizations has raised the possibility of data breaches and illicit data transfers. Traditional Data Loss Prevention (DLP) solutions, which use static rule-based procedures, frequently fail to detect complex cyber threats and insider misuse. This study describes an AI-driven DLP system that uses machine learning techniques to improve detection accuracy, reduce false positives, and enable adaptive policy enforcement. A synthetic dataset reflecting user activity and file access patterns was used to train algorithms such as Random Forest and K-Means clustering to detect abnormal activities. The experimental results show a significant improvement in detection accuracy (92%), as well as response time, when compared to conventional methods. The study finds that the incorporation of AI into DLP offers a potential option for current.
References:-
References
2. J. Lee and H. Park, "Machine Learning for Data Protection," Journal of Information Security, 8(2), 45-60, 2022.
3. R. Patel, M. Singh, and A. Gupta. "Adaptive Security Systems Using ML," ACM Transactions
on Privacy and Security, 2024.
4. A. Bajaj and S. Arora, "Intelligent Data Loss Prevention Framework Using Deep Learning," International Journal of Information Security Science, vol. 10, no. 3, 2021, pp. 85–98.
5. S. Khan, T. Ahmad, and F. Rahman, "Behavioral Analytics for Insider Threat Detection in Enterprise Systems," Computers & Security, vol. 120, no. 102832, 2022.
6. L. Nguyen, D. Pham, and M. Hoang. "Explainable AI Models for Cyber Threat Detection," IEEE Transactions on Information Forensics and Security, vol. 19, pp. 2034-2047, 2023.
7. Z. Zhang, H. Luo, and Y. Chen, "Enhancing Data Loss Prevention Systems with Machine Learning," IEEE Transactions on Dependable and Secure Computing, vol. 17, no. 5, 2018, pp. 1094–1107.
8. Sharma and Joshi, "Hybrid DLP Models Integrating Context-Aware Policies and AI," International Journal of Advanced Computer Science and Applications (IJACSA), vol. 13, no. 9, pp. 121-130, [222].
9. T. Chen, R. Zhang, and K. Huang, "Real-Time Anomaly Detection for Data Exfiltration using Unsupervised Learning," Future Generation Computer Systems, vol. 138,pp.456-468,2023.
10. M. Fernandes and L. Costa, "Federated Learning for Privacy-Preserving Security Systems," IEEE Internet of Things Journal, vol. 10, no. 14, pp. 12480–12493, 2023.
11. Inaganti, A. C., Ravichandran, N., and Muppalaneni, R. (2024). AI-Enhanced Data Loss Prevention (DLP) techniques for scenarios with multiple clouds. Computing Innovations and Applications Journal, 2, 1–13.
12. Miao, W. (2024). A deep learning approach to stop data leaking (Sensors or MDPI publication). Sensors (2024). [13] K. Gupta (2023). A classification model-based learning-oriented DLP system (preprint). arXiv. [14] HCLTech blog: How AI and ML are Transforming Data Loss Prevention (April 18, 2025)
13. HCLTech blog: How Data Loss Prevention is Being Revolutionized by AI and ML (Apr 18, 2025).
14. K. Gupta (2023). A classification model-based learning-oriented DLP system (preprint).
15. Mishra, A. April 18, 2025. Data Loss Prevention (DLP) is being revolutionized by AI and ML. blog for HCLTech.