Applying NIST Framework on Data Privacy Attacks Using K-Anonymity Algorithm
Thawit Sae-Ow, Chetneti Srisa-An, Jakarin Sirikulthorn · 2024
With the escalating frequency and complexity of data privacy attacks, organizations confront unprecedented challenges in safeguarding sensitive information. While the National Institute of Standards and Technology (NIST) has crafted a comprehensive framework to bolster cybersecurity measures, its application in the context of data privacy attacks remains relatively unexplored. This research paper seeks to delve into the efficacy of employing the NIST framework to mitigate data privacy attacks, scrutinizing its strengths and limitations, and proposing potential enhancements for a more resilient defense strategy. The experiment assesses the performance of various classification models on an original dataset. Subsequently, it evaluates the performance of the same classification models on a dataset modified by K-anonymity algorithms. The results of these classification model evaluations indicate that K-anonymity algorithms neither compromise data utility nor impede effectiveness, yielding higher scores.