Hello,
Decentralized AI
Train and run AI models as smart contracts fully onchain to benefit from the security, resilience, and computation power of the BigFile blockchain.
What is required to establish trust?
Model integrity
Users need guarantees that their AI prompts are answered by a model that has not been tampered with. Traditional techniques for assessing the integrity of software, such as source code analysis, are infeasible for AI models due to their large sizes.
Data confidentiality
During training and operation, AI models handle sensitive data, like medical inquiries or corporate secrets. Users need guarantees that their information remains secure and doesn't leak to the model creators, other users, or AI infrastructure providers.
Availability
AI models will become essential for business processes and societies in general. As with every critical infrastructure, solutions must be found to keep AI models resilient to interruptions and to protect them from censorship.
AI Models on BigFile Today
See a series of demos how the BigFile has the capability of running AI in a smart contract.
Experience the demo version
Check out the open-source repo on GitHub and tryout the AI demo by yourself.
// Setup:
let proto: ModelProto =
ModelProto::decode(onnx_file)?;
let model = tract_onnx::onnx()
.model_for_proto_model(&proto)?
.into_optimized()?
.into_runnable()?;
// Inference:
let result = model.run(tvec!
(Tensor::from(tensor).into()))?;
What the future holds
Blockchain AI is still in its early stages. Currently, smart contracts can run small AI models like ImageNet for onchain image classification. Short-term improvements will decrease latency and support larger models, while the long-term goal is to enable smart contracts to perform AI computations on GPUs, allowing both training and inference of large models fully onchain.
Detailed roadmap coming soon.
