Sensitive Data
Sensitive data protection is a critical area of research focusing on safeguarding private information during data analysis and machine learning model training. Current efforts concentrate on developing privacy-preserving techniques, including federated learning, differential privacy, and data sanitization methods like noise addition and data fragmentation, often implemented using large language models (LLMs) and other deep learning architectures. These advancements are crucial for enabling responsible data utilization across various sectors, particularly healthcare and finance, while mitigating privacy risks and ensuring compliance with regulations. The ultimate goal is to balance the utility of data with robust privacy protections.
Papers
Privacy-Preserving Machine Learning for Collaborative Data Sharing via Auto-encoder Latent Space Embeddings
Ana María Quintero-Ossa, Jesús Solano, Hernán Jarcía, David Zarruk, Alejandro Correa Bahnsen, Carlos Valencia
Secure Aggregation Is Not All You Need: Mitigating Privacy Attacks with Noise Tolerance in Federated Learning
John Reuben Gilbert