Software/algorithm Side: Model Verification

⚠️ Evaluation in Progress

Some of the mechanisms described on this page are currently being evaluated and validated. They represent design options under consideration, and may be refined, replaced, or omitted as the system evolves.

In addition to hardware-level TEE-based solutions for model verification, we will discuss our algorithmic approach to ensure model integrity. In decentralized inference systems, verifying that each node accurately executes the intended model is crucial for maintaining the integrity and reliability of the system. This verification process ensures consistency in inference results across the network, safeguards against malicious modifications of the model, and ensures adherence to privacy protocols and regulatory compliance. Moreover, it optimizes the use of computational resources, preventing wastage on incorrect or unauthorized computations, and helps manage operational costs effectively.

In the following section, we will introduce our use of zero-knowledge machine learning (ZKML) and consensus-based distribution verification (CDV) for model verification.