A Novel Cross-organization Privacy Protection Method Based on Federated Learning
Abstract
With the continuous development of science and technology, the degree of information in today's world is deepening, and the value of data information is becoming more and more important. At the same time, with the advancement of economic globalization, more and more users or business needs go beyond the traditional organizational boundaries, requiring multiple organizations to cooperate, and cross-organizational business management comes into being. Under the scenario of cross-organizational cooperation, protecting the business and data privacy of each organization has become a challenging task. Federated learning, as a new technology in the field of artificial intelligence, deals with both "data islands" and privacy protection. It can combine scattered data for training while maintaining the data privacy of each participating organization, and to a great extent, it protects sensitive data that needs to be fused. It has gradually become an effective means to solve the data and business privacy in cross-organizational business processes. This paper will combine federated learning to propose a cross-organizational privacy protection method based on federated learning to realize the privacy protection in cross-organizational business processes, and discuss the current challenges and future development direction to promote the further development of cross-organizational privacy protection methods.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.