Ratio Utility and Cost Analysis for Privacy Preserving Subspace Projection

The paper introduces RUCA (Ratio Utility and Cost Analysis), a novel method designed for privacy-preserving subspace projection that optimizes the utility-privacy trade-off in data classification tasks. RUCA employs a compressive-privacy approach to enhance performance in privacy-insensitive classification while minimizing the risk of private information leakage. Experimental results indicate that RUCA surpasses existing techniques on datasets such as Census and Human Activity Recognition, making it a valuable tool for practitioners focusing on data privacy in machine learning applications.