Core Concepts
Proposing AerisAI for secure decentralized AI collaboration with differential privacy and homomorphic encryption.
Abstract
Introduction to federated learning and privacy concerns.
Weaknesses in current FL systems: centralized server, lack of auditability, privacy issues.
Proposal of AerisAI: decentralized framework with homomorphic encryption and fine-grained differential privacy.
Features of AerisAI: blockchain-based, auditability, privacy preservation, group key management.
Theoretical analysis and comparison with baselines.
Experimental results showing AerisAI outperforms other baselines significantly.
Stats
"Our proposed AerisAI significantly outperforms the other state-of-the-art baselines."
"The experimental results indicate that the performance of the global model is not degraded by our proposed techniques."
Quotes
"Our proposed AerisAI significantly outperforms the other state-of-the-art baselines."
"The experimental results indicate that the performance of the global model is not degraded by our proposed techniques."