Data Obfuscation through Latent Space Projection (LSP) for Privacy-Preserving AI Governance: Case Studies in Medical Diagnosis and Finance Fraud Detection

TL;DR

This paper presents Latent Space Projection (LSP), a novel data obfuscation method that enhances privacy in AI systems by transforming sensitive data into a lower-dimensional, abstract space, balancing privacy and utility effectively.

Contribution

LSP introduces a new approach using autoencoders and adversarial training to obfuscate sensitive data in latent space, improving privacy while maintaining model performance.

Findings

LSP achieves 98.7% accuracy in healthcare diagnosis.

LSP provides 97.3% protection against sensitive attribute inference.

Outperforms traditional privacy-preserving methods in experiments.

Abstract

As AI systems increasingly integrate into critical societal sectors, the demand for robust privacy-preserving methods has escalated. This paper introduces Data Obfuscation through Latent Space Projection (LSP), a novel technique aimed at enhancing AI governance and ensuring Responsible AI compliance. LSP uses machine learning to project sensitive data into a latent space, effectively obfuscating it while preserving essential features for model training and inference. Unlike traditional privacy methods like differential privacy or homomorphic encryption, LSP transforms data into an abstract, lower-dimensional form, achieving a delicate balance between data utility and privacy. Leveraging autoencoders and adversarial training, LSP separates sensitive from non-sensitive information, allowing for precise control over privacy-utility trade-offs. We validate LSP's effectiveness through experiments on benchmark datasets and two real-world case studies: healthcare cancer diagnosis and financial fraud analysis. Our results show LSP achieves high performance (98.7% accuracy in image classification) while providing strong privacy (97.3% protection against sensitive attribute inference), outperforming traditional anonymization and privacy-preserving methods. The paper also examines LSP's alignment with global AI governance frameworks, such as GDPR, CCPA, and HIPAA, highlighting its contribution to fairness, transparency, and accountability. By embedding privacy within the machine learning pipeline, LSP offers a promising approach to developing AI systems that respect privacy while delivering valuable insights. We conclude by discussing future research directions, including theoretical privacy guarantees, integration with federated learning, and enhancing latent space interpretability, positioning LSP as a critical tool for ethical AI advancement.