Inferix Decentralized GPU
  • Getting Started
    • Overview
    • $IFX
    • Resources
    • Brand Kit
    • Frequently asked questions (FAQs)
  • Inferix Whitepaper
    • Introduction
      • Rendering network using crowdsourced GPU
      • Rendering verification problem
    • High-level description of ANGV
      • Noise generation
      • Noise verification
      • Thread model
    • Implementation of ANGV
      • Structure of noise
      • Noise insertion
        • Geometric constraints
        • Distortion region
      • Adaptive noise spreading
      • Verification key generation
      • Noise verification
      • Threat analysis
        • Attacks on verification keys
        • Attacks on noises
        • Attacks on verifiers
      • Performance evaluation
      • Integration
    • Decentralized visual computing
      • Client Apps plugin
      • Client API and SDK
      • Manager node
      • Worker node
      • Decentralized storage
        • Data categories
        • Multi-level 3D polygon data
        • Polygon digester
        • Decentralized storage
        • Decentralized cache
      • Data security with FHE and TEE
        • Verifier data security enhancement with FHE
        • Worker and Manager data security enhancement with FHE
    • Decentralized federated AI
      • Federated learning with TensorOpera
      • Meta LLaMA
      • Stable Diffusion
      • Other AI models
      • Inferix AI
    • Economic model
      • GPU compute market for visual computing and federated AI
      • Inferix vision
      • $IFX token
      • Burn-Mint-Work token issuance model
      • Inferix bench and IBME
        • IB and IBM
        • IBME
      • Price simulation
      • Token metrics and allocation
        • Token allocation
        • Token vesting
      • Governance
      • Node staking and rewards
        • Worker
        • Verifier
        • Manager
        • Penalty pool
      • Node sale and guaranteed node buyback
        • Node sales
        • Guaranteed Node Buyback
    • Future development
      • PoR and NFT minting for graphics creative assets
      • ZKP and PoR communication
      • Inferix RemotePC
      • Rendering professional network
    • References
    • Appendix A: Proofs
    • Appendix B: Price simulation details
    • Appendix C: Hardware requirements for nodes
    • Appendix D: Performance evaluation data
  • Worker Node Guide
    • What is Worker Node
      • How do the Worker Node work
      • Worker Node Rewards
      • How to run Worker Node
      • What is the Worker Node License (NFT)
    • Worker Node Sales
      • Guide to Purchase Worker Nodes
      • Worker Node Sale Timeline
      • Node Supply, Price, Tiers and Purchase Caps
      • Guaranteed Node Buyback
      • How to get Node Whitelisted?
      • Smart Contract Addresses
      • User Discounts & Referral Program
      • Worker Node Purchase FAQ
      • ABKK Collaboration FAQ
  • Verifier Node Guide
    • What is Verifier Node
      • How do the Verifier Node work
      • Verifier Node Rewards
      • How to run Verifier Node
      • What is the Verifier Node License (NFT)
    • Verifier Node Sales
      • Guide to Purchase Verifier Nodes
      • Verifier Node Sale Timeline
      • Node Supply, Price, Tiers and Purchase Caps
      • Guaranteed Node Buyback
      • How to get Node Whitelisted?
      • Smart Contract Addresses
      • User Discounts & Referral Program
      • Verifier Node Purchase FAQ
      • Aethir Node Winners FAQ
  • Inferix MVP
    • Tutorial: MVP for designers & GPU owners
    • PoR MVP
  • Inferix Testnet 2 on Solana & IoTeX [ENDED]
    • Adding GPUs to the Network
      • For GPU providers
      • For GPU providers without funds
      • For users without GPUs
      • For Inferix Node Holders
    • Renting GPU Devices
    • User Revenue Calculation
      • Worker Rewards
      • Rental Revenue
      • Viewing Revenue
      • Claiming Rewards
    • GPU Staking & Unstaking
      • Staking Requirements
      • Unstaking GPUs
    • Guide to get tIFX tokens
    • Why choose Inferix DePIN GPU Solutions?
  • Inferix Testnet 1 on IoTeX [ENDED]
    • Inferix GPU Solutions
    • Adding GPUs to the Network
    • Renting GPU Devices
    • User Revenue Calculation
    • GPU Staking
    • Multiple options to participate in the Staking & Mining Program
    • Special airdrop for Inferix Node Holders! 🎉
    • Guide to get tIFX tokens
    • FAQ
  • Inferix Explorer
  • Team & Achievements
    • Our Story
    • Team
    • Member of Cohort 1 DePINSurf
    • Achievements
  • Community & Events
    • Events
    • Inferix Campaign: "ALLIANCE" (ENDED)
  • Terms of Service
    • Privacy Policy
    • Airdrop Terms of Service
Powered by GitBook
On this page
  1. Inferix Whitepaper
  2. Implementation of ANGV
  3. Noise insertion

Distortion region

PreviousGeometric constraintsNextAdaptive noise spreading

Last updated 8 months ago

Under constraints about position and direction of noise objects, the imprint of ωi\omega_iωi​ on the rendered image is a rectangular region denoted by:

ki≜(xiul,yiul,xilr,yilr)k_i \triangleq \left(x_i^{\mathtt{ul}}, y_i^{\mathtt{ul}}, x_i^{\mathtt{lr}}, y_i^{\mathtt{lr}} \right)ki​≜(xiul​,yiul​,xilr​,yilr​)

where (xiul,yiul)\left(x_i^{\mathtt{ul}}, y_i^{\mathtt{ul}}\right)(xiul​,yiul​) and (xilr,yilr)\left(x_i^{\mathtt{lr}}, y_i^{\mathtt{lr}}\right)(xilr​,yilr​) are respectively the upper left and lower right positions in the image coordinate system. It is important to note that $k_i$ for all 1≤i≤n1 \leq i \leq n1≤i≤n can be computed without rendering the scene GGG.

For the size of distortion regions, similar with the length of the noise random vector, there is a compromise between the robustness of the embedded noise and the fidelity of the rendered frame. The larger the distortion kik_iki​, the higher information of wiw_iwi​ can be restored then the higher robustness of the noise verification; but the lower the distortion kik_iki​, the higher fidelity of the image. Empirically, we use the bounds 4≤xilr−xiul, yilr−yiul≤74 \leq x^{\mathtt{lr}}_{i} - x^{\mathtt{ul}}_{i},\ y^{\mathtt{lr}}_{i} - y^{\mathtt{ul}}_{i} \leq 74≤xilr​−xiul​, yilr​−yiul​≤7 for all 1≤k≤n1 \leq k \leq n1≤k≤n.

The figure above shows some distortion results of rendering watermarked scenes. From two original scenes, noise vectors of length 121212 with different distortion sizes are embedded, then different watermarked scenes are generated. When rendering the scenes containing noises whose distortion sizes are 777 or 888, the distortions are visible under the form of small rectangles dispersed in the rendered images. In contrast, when the sizes are 444 or 555, the distortions are imperceptible.

Remark: While the atomic watermarks are quite large, the distortions made by them on rendered images are constrained relatively small. The figure in the previous section shows atomic watermarks of size 512×512512 \times 512512×512 which are used for watermarking scenes shown in the figure above, their imprints are about 4×44 \times 44×4. The sizes of the rendered images are much larger: 1080×10801080 \times 10801080×1080 and 1920×10801920 \times 10801920×1080.

Rendered watermarked scenes (random vector length 12)