Developing a Decentralized AI Model Training Framework Using Blockchain Technology

Main Article Content

Snehal Satish
Karthik Meduri
Geeta Sandeep Nadella
Hari Gonaygunta

Abstract

This research addresses the critical challenges in traditional centralized AI model training, focusing on data privacy, security, and the risks associated with centralized data repositories. Integrating blockchain technology with AI model training aims to develop a decentralized framework that enhances data integrity and trustworthiness while mitigating vulnerabilities inherent in centralized systems. The objectives include designing and evaluating a blockchain-based infrastructure that supports security and collaboration. In the AI-model training, we leverage federated learning to enable data privacy-preserving mechanisms. The importance of this research lies in its ability to transfigure the current landscape of AI development by providing a robust solution that decentralizes data management, ensures transparency through immutable ledger technology, and automates secure interactions via smart contracts. Key contributions include conceptualizing and implementing a blockchain framework tailored for AI model training and incorporating decentralized data storage and smart contracts for task automation of federated learning for collaborative model development. Findings from experimental evaluations using the MNIST dataset demonstrate the framework's effectiveness in maintaining data privacy and enhancing security while achieving high client-produced accuracy (91%) and acknowledging challenges in generalizing model performance across heterogeneous datasets.

Downloads

Download data is not yet available.

Article Details

How to Cite
Developing a Decentralized AI Model Training Framework Using Blockchain Technology. (2022). International Meridian Journal, 4(4), 1-20. https://meridianjournal.in/index.php/IMJ/article/view/71
Section
Articles

How to Cite

Developing a Decentralized AI Model Training Framework Using Blockchain Technology. (2022). International Meridian Journal, 4(4), 1-20. https://meridianjournal.in/index.php/IMJ/article/view/71

References

Fadaeddini, A., Majidi, B. and Eshghi, M., 2020. Secure decentralized peer-to-peer training of deep neural networks based on distributed ledger technology. The Journal of Supercomputing, 76(12), pp.10354-10368.

Harris, J.D. and Waggoner, B., 2019, July. Decentralized and collaborative AI on blockchain. In 2019 IEEE international conference on blockchain (Blockchain) (pp. 368-375). IEEE.

Adel, K., Elhakeem, A. and Marzouk, M., 2022. Decentralizing construction AI applications using blockchain technology. Expert Systems with Applications, 194, p.116548.

Gupta, I., 2020. Decentralization of artificial intelligence: analyzing developments in decentralized learning and distributed AI networks. arXiv preprint arXiv:1603.04467.

Harris, J.D., 2020. Analysis of models for decentralized and collaborative AI on blockchain. In Blockchain–ICBC 2020: Third International Conference, Held as Part of the Services Conference Federation, SCF 2020, Honolulu, HI, USA, September 18-20, 2020, Proceedings 3 (pp. 142-153). Springer International Publishing.

Nassar, M., Salah, K., ur Rehman, M.H. and Svetinovic, D., 2020. Blockchain for explainable and trustworthy artificial intelligence. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 10(1), p.e1340.

Team, NA, 2018. Nebula ai (nbai)—decentralized ai blockchain whitepaper.

Fadaeddini, A., Majidi, B. and Eshghi, M., 2019. Privacy preserved decentralized deep learning: A blockchain based solution for secure ai-driven enterprise. In High-Performance Computing and Big Data Analysis: Second International Congress, TopHPC 2019, Tehran, Iran, April 23–25, 2019, Revised Selected Papers 2 (pp. 32-40). Springer International Publishing.

Mamoshina, P., Ojomoko, L., Yanovich, Y., Ostrovski, A., Botezatu, A., Prikhodko, P., Izumchenko, E., Aliper, A., Romantsov, K., Zhebrak, A. and Ogu, I.O., 2018. Converging blockchain and next-generation artificial intelligence technologies to decentralize and accelerate biomedical research and healthcare. Oncotarget, 9(5), p.5665.

Phansalkar, S., Kamat, P., Ahirrao, S. and Pawar, A., 2019. Decentralizing AI applications with block chain. International Journal of Scientific & Technology Research, 8(9), p.9.

Ahmed, I., Zhang, Y., Jeon, G., Lin, W., Khosravi, MR and Qi, L., 2022. A blockchain‐and artificial intelligence‐enabled smart IoT framework for sustainable city. International Journal of Intelligent Systems, 37(9), pp.6493-6507.

Morsbach, F. and Toor, S., 2021, May. DecFL: An Ubiquitous Decentralized Model Training Protocol and Framework Empowered by Blockchain. In Proceedings of the 3rd ACM International Symposium on Blockchain and Secure Critical Infrastructure (pp. 61-70).

Khan, A.A., Khan, M.M., Khan, K.M., Arshad, J. and Ahmad, F., 2021. A blockchain-based decentralized machine learning framework for collaborative intrusion detection within UAVs. Computer Networks, 196, p.108217.

Li, Y., Chen, C., Liu, N., Huang, H., Zheng, Z. and Yan, Q., 2020. A blockchain-based decentralized federated learning framework with committee consensus. IEEE Network, 35(1), pp.234-241.

Ouyang, L., Yuan, Y. and Wang, F.Y., 2020. Learning markets: An AI collaboration framework based on blockchain and smart contracts. IEEE Internet of Things Journal, 9(16), pp.14273-14286.

Tagde, P., Tagde, S., Bhattacharya, T., Tagde, P., Chopra, H., Akter, R., Kaushik, D. and Rahman, M.H., 2021. Blockchain and artificial intelligence technology in e-Health. Environmental Science and Pollution Research, 28, pp.52810-52831.

Zanardo, E., 2022. Learningchain. A novel blockchain-based meritocratic marketplace for training distributed machine learning models. In Proceedings of the Computational Methods in Systems and Software (pp. 152-169). Cham: Springer International Publishing.

Tagde, P., Tagde, S., Bhattacharya, T., Tagde, P., Chopra, H., Akter, R., ... & Rahman, M. H. (2021). Blockchain and artificial intelligence technology in e-Health. Environmental Science and Pollution Research, 28, 52810-52831.

ul Haque, A., Ghani, M.S. and Mahmood, T., 2020, January. Decentralized transfer learning using blockchain & IPFS for deep learning. In 2020 International Conference on Information Networking (ICOIN) (pp. 170-177). IEEE.

Cao, L., 2022. Decentralized ai: Edge intelligence and smart blockchain, metaverse, web3, and desci. IEEE Intelligent Systems, 37(3), pp.6-19.

Singh, S.K., Rathore, S. and Park, J.H., 2020. Blockiotintelligence: A blockchain-enabled intelligent IoT architecture with artificial intelligence. Future Generation Computer Systems, 110, pp.721-743.

Roosan, D., Wu, Y., Tatla, V., Li, Y., Kugler, A., Chok, J. and Roosan, M.R., 2022. Framework to enable pharmacist access to health care data using Blockchain technology and artificial intelligence. Journal of the American Pharmacists Association, 62(4), pp.1124-1132.

Vikhyath, K.B., Sanjana, R.K. and Vismitha, N.V., 2022. Intersection of AI and blockchain technology: Concerns and prospects. In The International Conference on Deep Learning, Big Data and Blockchain (Deep-BDB 2021) (pp. 53-66). Springer International Publishing.

Kuo, T.T. and Ohno-Machado, L., 2018. Modelchain: Decentralized privacy-preserving healthcare predictive modeling framework on private blockchain networks. arXiv preprint arXiv:1802.01746.

Sahal, R., Alsamhi, S.H., Brown, K.N., O'Shea, D. and Alouffi, B., 2022. Blockchain‐Based Digital Twins Collaboration for Smart Pandemic Alerting: Decentralized COVID‐19 Pandemic Alerting Use Case. Computational Intelligence and Neuroscience, 2022(1), p.7786441.

Singh, S., Rathore, S., Alfarraj, O., Tolba, A. and Yoon, B., 2022. A framework for privacy-preservation of IoT healthcare data using Federated Learning and blockchain technology. Future Generation Computer Systems, 129, pp.380-388.

Balcerzak, A.P., Nica, E., Rogalska, E., Poliak, M., Klieštik, T. and Sabie, O.M., 2022. Blockchain technology and smart contracts in decentralized governance systems. Administrative Sciences, 12(3), p.96.

Wang, R., Luo, M., Wen, Y., Wang, L., Raymond Choo, K.K. and He, D., 2021. The applications of blockchain in artificial intelligence. Security and Communication Networks, 2021(1), p.6126247.

Maksymyuk, T., Gazda, J., Volosin, M., Bugar, G., Horvath, D., Klymash, M. and Dohler, M., 2020. Blockchain-empowered framework for decentralized network management in 6G. IEEE Communications Magazine, 58(9), pp.86-92.

Sai, S., Chamola, V., Choo, K.K.R., Sikdar, B. and Rodrigues, J.J., 2022. Confluence of blockchain and artificial intelligence technologies for secure and scalable healthcare solutions: A review. IEEE Internet of Things Journal, 10(7), pp.5873-5897.

Kazerouni, A., Zhao, Q., Xie, J., Tata, S., & Najork, M. (2020). Active learning for skewed data sets. arXiv preprint arXiv:2005.11442.

Vijayaraj, A., Vasanth Raj, P. T., Jebakumar, R., Gururama Senthilvel, P., Kumar, N., Suresh Kumar, R., & Dhanagopal, R. (2022). Deep learning image classification for fashion design. Wireless Communications and Mobile Computing, 2022(1), 7549397.

Burlachenko, K., Horváth, S., & Richtárik, P. (2021, December). Fl_pytorch: optimization research simulator for federated learning. In Proceedings of the 2nd ACM International Workshop on Distributed Machine Learning (pp. 1-7).

Zhang, C., Xie, Y., Bai, H., Yu, B., Li, W., & Gao, Y. (2021). A survey on federated learning. Knowledge-Based Systems, 216, 106775.

Kadam, S. S., Adamuthe, A. C., & Patil, A. B. (2020). CNN model for image classification on MNIST and fashion-MNIST dataset. Journal of scientific research, 64(2), 374-384.

Korkmaz, C., Kocas, H. E., Uysal, A., Masry, A., Ozkasap, O., & Akgun, B. (2020, November). Chain fl: Decentralized federated machine learning via blockchain. In 2020 Second international conference on blockchain computing and applications (BCCA) (pp. 140-146). IEEE.

Mammen, P. M. (2021). Federated learning: Opportunities and challenges. arXiv preprint arXiv:2101.05428.

Most read articles by the same author(s)