Auditable Homomorphic-based Decentralized Collaborative AI with Attribute-based Differential Privacy

arXiv:2403.00023v1 Announce Type: new
Abstract: In recent years, the notion of federated learning (FL) has led to the new paradigm of distributed artificial intelligence (AI) with privacy preservation. However, most current FL systems suffer from data privacy issues due to the requirement of a trusted third party. Although some previous works introduce differential privacy to protect the data, however, it may also significantly deteriorate the model performance. To address these issues, we propose a novel decentralized collaborative AI framework, named …

artificial artificial intelligence arxiv cs.ai cs.cr cs.lg current data data privacy decentralized differential privacy distributed federated federated learning intelligence led notion paradigm party preservation privacy systems third