Safeguarding Student Data Privacy: A Comparative Study of Anonymization Techniques Using the Mondrian Algorithm

Data has become a critical and valuable tool in today's digital environment. The numerous benefits of data, such as business, research, and education, are not immune to potential threats to individuals' privacy and security. Law No. 27 of 2022 emphasizes the necessity to safeguard the privacy and security of individuals whose data are made public. Data anonymization is a technique that can protect the privacy of individuals in a database. K-anonymity, l-diversity, t-closeness, generalization, and suppression are methods that can be used to anonymize the data. The Mondrian method can be used for k-anonymity, l-diversity, and t-closeness. Furthermore, the Normalized Certainty Penalty (NCP) is used to evaluate the extent of data loss or distortion caused by anonymization. The Mondrian algorithm is applied to the student dataset. The objective is to generate anonymized data with high values. The study involved three anonymization scenarios, with k and l set to three, four, and five, respectively. The results indicated that the first experiment performed well, with k and l values set to three, achieving an average T closeness value of 0.503 and an NCP value of 15.7%.