Blockchain-Enabled Federated Learning for Fair and Transparent AI

@article{1710547,
      author = {Sangram Bhimdas Jadhav},
      title = {Blockchain-Enabled Federated Learning for Fair and Transparent AI},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {9},
      number = {3},
      pages = {608-610},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1710547.pdf},
      abstract = {Federated Learning (FL) enables collaborative model training across decentralized data sources without sharing raw data, but it introduces fairness concerns and lacks transparency in model updates. This paper proposes a blockchain-enabled federated learning framework to enhance fairness and accountability. By recording model updates, metadata, and fairness metrics on a distributed ledger, blockchain provides auditability, immutability, and trust among participants. We evaluate the conceptual design and simulate its performance on benchmark datasets. Results highlight that blockchain integration improves fairness auditing and transparency with modest computational overhead. This study provides practical insights into how blockchain can reinforce trust in distributed AI systems.},
      keywords = {Blockchain, Federated Learning, Fair AI, Transparency, Accountability, Data Science.},
      month = {September},
  }