nChain Announces First Implementation of Verifiable AI on Bitcoin

Leading experts at nChain have identified and successfully tested ways in which the output of an AI system can be verified using a blockchain. This can be used to ensure the model operates according to its specifications, is free of critical bugs, and adheres to ethical standards such as fairness, transparency, and safety.  All without revealing proprietary information of the system – a major step in bringing trust and accountability to AI.

Also Read: Unilever and Accenture Join Forces to Establish a New Industry Standard in Generative AI-Powered Productivity

nChain successfully demonstrated verifiable AI inference (processing queries) on Bitcoin showing the relevant transactions on the original protocol Bitcoin, Bitcoin Satoshi Vision Blockchain (BSV Blockchain). The transactions can be found on mainnet with corresponding generation code on Github.

While this is a relatively new research area, and something nChain only recently started exploring, after having successfully implemented verifiable computation on Bitcoin the team challenged themselves to see if it could also apply this to machine learning.

“Training is computation. Inference is computation. If you can do verifiable computation, then you can do verifiable training or verifiable inference,” says Dr. Hamid Attar, lead AI Researcher at nChain.

The team trained a simple neural network on the MNIST dataset of images of hand-written digits. The model was then run on an input image, such as one provided by a user, and produced an output predicting which digit the input image represents. A cryptographic proof was generated to verify the output was indeed produced by running the model on the specified image while hiding all the information about the model. The proof was subsequently used to claim a small amount of bitcoin from the blockchain – in this case from the user. Here, Bitcoin not only provides a decentralised independent verification platform but also facilitates micro payment between a user and an AI model.

Also Read: AiThority Interview with Paul Fipps, President, Global Industries and Strategic Growth at ServiceNow

With verifiable computation approach, nChain can prove cryptographically that an AI model is trained on the claim dataset. For example, it can be proven that a generative AI model is trained on a dataset that is known to have no bias.  More importantly, AI developers can prove that they did not tamper with the training dataset to train an AI model for malicious intentions. nChain can also prove that an output of an AI mode is obtained by running the specified AI model on the given input. For example, a piece of artwork can have a proof showing that it is generated by an AI model on a given prompt,  or as a paid user you can be sure that you are getting answers from ChatGPT4 not the free versions.

[To share your insights with us as part of editorial or sponsored content, please write to psen@itechseries.com]