Abstract
In the era of artificial intelligence, ensuring privacy in publicly released data is critical to prevent linkage attacks that can reveal sensitive information about individuals. Differential privacy (DP) has emerged as a robust approach for safeguarding privacy, but its mathematical complexity often limits its accessibility to non-experts. This paper introduces a novel, user-friendly web application that bridges the gap between theoretical DP concepts and their practical application. The application includes two main features: a query version, which demonstrates DP mechanisms for statistical queries; and a privatize version, which applies DP techniques to entire datasets. A key contribution of this work is the identification of discrepancies in the implementation of maximum and minimum queries within the OpenDP library, revealing gaps between theory and practice. Additionally, this paper introduces a foundational framework for dataset privatization using OpenDP's built-in methods. By providing an interactive platform, this work advances the public understanding of DP mechanisms and highlights areas for improvement in existing libraries. The application serves as both an educational tool and a step toward addressing practical challenges in the implementation of DP.