Privacy-Preserving AI Collaboration on Blockchain Using Aggregate Signatures with Public Key Aggregation

The integration of artificial intelligence (AI) and blockchain technology opens new avenues for decentralized, transparent, and secure data-driven systems. However, ensuring privacy and verifiability in collaborative AI environments remains a key challenge, especially when model updates or decisions must be recorded immutably on-chain. In this paper, we propose a novel privacy-preserving framework that leverages an ElGamal-based aggregate signature scheme with aggregate public keys to enable secure, verifiable, and unlinkable multi-party contributions in blockchain-based AI ecosystems. This approach allows multiple AI agents or data providers to jointly sign model updates or decisions, producing a single compact signature that can be publicly verified without revealing the identities or individual public keys of contributors. The design is particularly well-suited to resource-constrained or privacy-sensitive applications such as federated learning in healthcare or finance. We analyze the security of the scheme under standard assumptions and evaluate its efficiency in different terms. The study and experimental results demonstrate the potential of our framework to enhance trust and privacy in AI collaborations over decentralized networks.

• aggregate signatures
• blockchain
• ElGamal signature scheme
• unlinkability
• federated learning

• Cryptography and Data Security
• Blockchain Technology Applications and Security
• Blockchain Technology in Education and Learning
• aggregate signatures
• blockchain
• ElGamal signature scheme
• unlinkability
• federated learning
• Artificial Intelligence
• Information Systems
• Computer Science