ORA
TwitterDiscordWebsiteMirror
  • ✨Quick Start
  • 🔘Introduction
    • About ORA
    • Use Cases
    • Key Milestones
  • 🌐Foundation
    • ORA Coin ($ORA)
    • Tokenomics
      • Interacting with ORA’s Tokenomics
  • 🤖Onchain Perpetual Agent (opAgent)
    • opAgent
  • 🔮Onchain AI Oracle (OAO)
    • Onchain AI Oracle
      • Build with AI Oracle
        • Callback Gas Limit Estimation
        • Advanced Usages of AI Oracle
        • Optimistic Machine Learning (OPML)
      • Onboard AI Models
      • Non-Developer Guides
      • References
        • AI Settlement Oracle
        • Example: Fortune Teller
    • Node Operator Guide
      • Tora Validator Client
      • Tora Launcher - Tutorial
      • Tora CLI - Tutorial
      • Troubleshooting
    • Fraud Proof Virtual Machine (FPVM) and Frameworks
      • opML
      • opp/ai
      • Comparison of Proving Frameworks
  • 💠Resilient Model Services (RMS)
    • Overview
    • ORA API
    • Model and Pricing
    • Technology
  • 🪙INITIAL MODEL OFFERING (IMO)
    • IMO Overview
    • IMO Participation Rules
    • ERC-7641: Intrinsic RevShare Token
    • ERC-7007: Verifiable AI-Generated Content Token
  • 📚Resources
    • Resources
    • FAQ
    • Glossary
    • Legal
      • Privacy Policy
      • Terms of Use
  • 📧Get in touch
    • Twitter
    • Telegram
    • GitHub
Powered by GitBook
On this page
  • opML vs zkML
  • opp/ai

Was this helpful?

Export as PDF
  1. Onchain AI Oracle (OAO)
  2. Fraud Proof Virtual Machine (FPVM) and Frameworks

Comparison of Proving Frameworks

Previousopp/aiNextOverview

Last updated 1 year ago

Was this helpful?

opML vs zkML

ORA leverages opML for Onchain AI Oracle because it’s the most feasible solution on the market for running any-size AI model onchain. The comparison between opML and zkML can be viewed from the following perspectives:

  • Proof system: opML uses fraud proofs, while zkML uses zk proofs.

  • Performance: opML is much more performant, while zkML has long proof generation time and extremely high memory consumption (, , , , , ).

  • Security: opML uses crypto-economic based security, while zkML uses cryptography based security.

  • Finality: We can define the finalized point of zkML and opML as follows:

    • zkML: Zero-knowledge proof of ML inference is generated (and verified).

    • opML: Challenge period of ML inference is passed. With additional mechanisms, faster finality can be achieved in much shorter time than the challenge period.

opp/ai

Opp/AI combines both opML and zkML approaches to achieve scalability and privacy. It preserves privacy while being more efficient than zkML.

Compared to pure zkML, opp/ai has much better performance with the same privacy feature.

🔮
ref1
ref2
ref3
ref4
ref5
ref6