Decentralized AI Model Training and Inference Using Blockchain for Privacy- Preserving Federated Learning.

Federated Learning (FL) has emerged as a promising approach to training machine learning models across distributed devices while preserving data privacy by avoiding centralized data collection. However, traditional FL frameworks rely on a central server to aggregate model updates, introducing vulnerabilities such as single-point failures, lack of transparency, and susceptibility to adversarial attacks like model poisoning. To address these challenges, this paper proposes a decentralized AI training and inference framework that integrates blockchain technology with FL to enhance security, privacy, and trust. Our framework leverages smart contracts to automate model aggregation, decentralized storage for secure weight distribution, and cryptographic techniques such as homomorphic encryption and zero-knowledge proofs to ensure privacy-preserving validation. By eliminating the need for a central authority, our approach enhances robustness against malicious actors while maintaining model accuracy comparable to traditional FL. Additionally, we introduce a consensus mechanism that verifies participant contributions, ensuring fairness and auditability. Experimental evaluations on benchmark datasets demonstrate that our framework achieves competitive performance while significantly improving privacy and resistance to attacks. This work bridges the gap between decentralized AI and federated learning, offering a scalable and secure solution for privacy-sensitive applications in healthcare, finance, and IoT. Future research directions include optimizing blockchain scalability and exploring incentive mechanisms for sustainable participation.