From Encryption to Anonymization: Safeguarding Privacy in Data Mining

Thanu Priya N., Sheeja Kumari V, John Peter K

2025

Abstract

In the big data age, data mining has proven to be an important source of getting useful information in every area of life. But definitely the ever increasing volume and confidentiality of the data also raised issues of exposure and abuse of data. The aim of this paper is to examine a variety of privacy-enhancing technologies such as encryption and anonymization and their utility in solving these problems. Encryption protects the information during its various phases (storage, transfer, or computation)which allows secure working and sharing of information. Meanwhile, anonymizing methods(k-anonymization, l-diversity, or differential privacy) are able to cover individual’s identity by minimizing information in the databases. While these approaches provide unique strengths, they also face limitations, such as trade-offs between data utility and privacy protection, or even advanced re-identification attacks. This research emphasizes the hybrid nature of encryption and anonymization, proposing a structure that avoids obstacles when trying to combine these strategies. Likewise discussed are new types of technologies, such as synthetic data generation, federated learning and homomorphic encryption, which are likely to revolutionize the way secure data mining is perceived. With the suggested generative model accuracy of 92%, precision 0.91, recall 0.94 and F1 score of 0.92, the case is illustrated as to how the integration of high performance and privacy-preserving data mining techniques can be accomplished. With an AUC-ROC of 0.95, the model processes efficiently in real time. It classifies with accuracy and recall locking down 15 minutes for training and 1.2 seconds for inference. Tackling the technical, ethical, and legal aspects, this work argues to establish privacy-respecting frameworks to build confidence in data-informed innovations. The aim of these insights is to help scientists, practitioners, and decision-makers to think forward toward the age wherein privacy and data analytics will coexist peacefully.

Paper Citation

in Harvard Style

N. T., V S. and K J. (2025). From Encryption to Anonymization: Safeguarding Privacy in Data Mining. In Proceedings of the 3rd International Conference on Futuristic Technology - Volume 3: INCOFT; ISBN 978-989-758-763-4, SciTePress, pages 920-929. DOI: 10.5220/0013735000004664

in Bibtex Style

@conference{incoft25,
author={Thanu Priya N. and Sheeja Kumari V and John Peter K},
title={From Encryption to Anonymization: Safeguarding Privacy in Data Mining},
booktitle={Proceedings of the 3rd International Conference on Futuristic Technology - Volume 3: INCOFT},
year={2025},
pages={920-929},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013735000004664},
isbn={978-989-758-763-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 3rd International Conference on Futuristic Technology - Volume 3: INCOFT
TI - From Encryption to Anonymization: Safeguarding Privacy in Data Mining
SN - 978-989-758-763-4
AU - N. T.
AU - V S.
AU - K J.
PY - 2025
SP - 920
EP - 929
DO - 10.5220/0013735000004664
PB - SciTePress