The increasing use of data-centric approaches in the fields of Machine Learning and Artificial Intelligence (ML/ AI) has raised substantial issues over the security, integrity, and trustworthiness of data. In response to this challenge, Blockchain technology offered a promising and practical solution as its inher-ent characteristics as a decentralized distributed ledger, coupled with cryptographic processes, offer an unprecedented level of data confidentiality and immutability. This study examines the mutually beneficial connection between Blockchain technology and ML/ AI, using Blockchain's inherent capacity to protect against unauthorized alterations of data during the training phase of ML models. The technique includes the development of data blocks obtained from the training dataset and subsequent submission to the mining process via the use of smart contracts and the adoption of the Proof-of-Federated-Learning (PoFL) consensus method. The aforementioned procedure is enhanced by the use of Secure Multi-Party Computation (SMPC) in order to generate a cryptographic signature for every individual data block. These signatures are securely stored within a cloud-based architecture and serve a crucial role in the data verification process during the training phase of ML models. This Work-in-Progress (WiP) research investigates the potential collaboration between Blockchain technology and ML/ AI, bolstering data qual-ity and trust to enhance data-driven decision-making fortifying the models' ability to provide precise and dependable results.