A Novel Agent-Based Framework for Data Leakage Detection Using Intelligent Data Allocation and Guilt Analysis
Keywords:
Agent-based model, Concept drift, Data leakage detection, Data mining, Data security, Fake data injection, Guilt probability model, Privacy preservationAbstract
Data leakage has become a critical concern in distributed and data-driven environments, especially with the increasing reliance on cloud computing and third-party data sharing. Traditional approaches, such as watermarking and encryption, provide limited capabilities in identifying the exact source of leakage. This paper proposes a novel agent-based framework for data leakage detection using intelligent data allocation and guilt analysis. The proposed system distributes data among multiple agents in a controlled manner and injects unique fake data objects to enhance traceability. When leakage occurs, a guilt probability model is applied to analyze the leaked dataset and identify the most likely responsible agent. Additionally, the framework incorporates concept drift detection to adapt to changes in data patterns over time, ensuring consistent performance in dynamic environments. Experimental results demonstrate that the proposed method significantly improves detection accuracy compared to existing techniques, achieving up to 95% accuracy while maintaining efficient detection time. The system also shows scalability as the number of agents increases. Overall, the proposed approach provides a robust, reliable, and practical solution for data leakage detection without modifying the original data, making it suitable for real-world applications such as cloud computing, enterprise systems, and secure data sharing platforms.
References
Y. Lindell, “Secure multiparty computation for privacy preserving data mining,” Journal of Privacy and Confidentiality, vol. 10, no. 1, 2020.
M. Conti, A. Dehghantanha, K. Franke, and S. Watson, “Internet of Things security and forensics: Challenges and opportunities,” Future Generation Computer Systems, vol. 78, pp. 544–546, 2020.
R. Shokri, M. Stronati, C. Song, and V. Shmatikov, “Membership inference attacks against machine learning models,” IEEE Symposium on Security and Privacy, 2020.
N. Z. Gong and B. Liu, “Attribute inference attacks in online social networks,” ACM Transactions on Privacy and Security, vol. 21, no. 1, 2020.
J. Gama, I. Žliobaitė, A. Bifet, M. Pechenizkiy, and A. Bouchachia, “A survey on concept drift adaptation,” ACM Computing Surveys, updated version, 2021.
H. Hu, Z. Salcic, L. Sun, G. Dobbie, and X. Zhang, “Membership inference attacks on machine learning: A survey,” ACM Computing Surveys, vol. 54, no. 11, 2022.
H. Wang, “Privacy-Preserving Data Sharing in Cloud Computing,” Journal of Computer Science and Technology, vol. 25, no. 3, pp. 401–414, May 2010.
J. Wang, N. Wang, W. Zhou, J. Liu, J. Fu, and L. Deng, “A Privacy-Preserving IoT Data Access Control Scheme for Cloud-Edge Computing,” IEEE Transactions on Parallel and Distributed Systems, vol. 36, no. 12, pp. 2549–2565, Dec. 2025.
H. H. Bin Suhaimi and H. T. Zubair, “Data Leakage Detection in Cloud Computing Environment,” 2024 1st International Conference on Cyber Security and Computing (CyberComp), pp. 7–12, Nov. 2024.
K. Zhang, J. Ni, K. Yang, X. Liang, J. Ren, and X. S. Shen, “Security and Privacy in Smart City Applications: Challenges and Solutions,” IEEE Communications Magazine, vol. 55, no. 1, pp. 122–129, Jan. 2017.
