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
Protecting Activity Sensing Data Privacy Using Hierarchical Information Dissociation
Guangjing Wang, Hanqing Guo, Yuanda Wang, Bocheng Chen, Ce Zhou, Qiben Yan
Do Large Language Models Possess Sensitive to Sentiment?
Yang Liu, Xichou Zhu, Zhou Shen, Yi Liu, Min Li, Yujun Chen, Benzi John, Zhenzhen Ma, Tao Hu, Zhi Li, Zhiyang Xu, Wei Luo, Junhui Wang
Assessing the Impact of Image Dataset Features on Privacy-Preserving Machine Learning
Lucas Lange, Maurice-Maximilian Heykeroth, Erhard Rahm
Large Language Models for Automatic Detection of Sensitive Topics
Ruoyu Wen, Stephanie Elena Crowe, Kunal Gupta, Xinyue Li, Mark Billinghurst, Simon Hoermann, Dwain Allan, Alaeddin Nassani, Thammathip Piumsomboon