
Yanez
ت (Teh)SN54Yanez SN54 generates synthetic identities for challenging Yanez humanhood, presence, and uniqueness detection models.
Overview
Registration Activity
Neuron registration trends

Yanez SN54 generates synthetic identities for challenging Yanez humanhood, presence, and uniqueness detection models.
Neuron registration trends
The alpha price in τ, day by day, and what moved it each way.
Log change over the last 30 days −14.17%: protocol buys +0.04%, root sells −1.41%, users net +9.48%, cross-subnet −22.28%, unattributed +0.0003%.
The chart follows the alpha price in τ. Each period starts at its opening price and steps through the mechanisms below, in a fixed order, to its closing price: a step that rises pushed the price up, one that falls pushed it down, and its height is how far it moved the price. A thin line carries each close into the next period’s open; it is dashed where the two differ. The faint candle behind each period is the market’s own open, high, low and close, for context.
With many periods on screen (90 days, or hours), the steps would be too thin to read, so the chart draws the price as a line instead and colours each period by the mechanism that moved it most. Hover a period for the full step-by-step breakdown.
Not here, because they do not move the spot price: the per-block TAO injection into the pool, and burns.
All figures are log changes, not simple percentage changes, so the parts add up exactly to the total; on big moves the two differ (a 10% log fall is a 9.5% price fall).
2026-11-07 UTC, as of ≈00:30 UTC (block 9,450,643)
The day isn’t over yet, so these figures keep changing. They are in no daily total, average or rank.
Financial institutions, fintech platforms, and biometric security teams struggle to test KYC and identity verification systems against presentation attacks, screen replays, and facial transformations. Current approaches rely on limited public datasets, manual capture of screen-replay attacks, or proprietary synthetic generation that doesn't scale. Testing deepfake resistance and liveness detection requires diverse, identity-preserving facial variations—but generating sufficient volume while maintaining ground-truth identity preservation is expensive and slow.
A decentralized network of contributors can generate high-quality facial variations at scale, with economic incentives driving both quality and throughput. Validators evaluate submissions through automated identity checks and manual review, ensuring the dataset remains fit for real-world testing. Miners are rewarded based on how well they preserve identity while applying the exact transformations requested—creating a direct financial incentive to solve the problem well.
Yanez (Subnet 54 on Bittensor) implements this as a live marketplace: validators issue standardized face variation challenges (background changes, lighting/expression/pose edits, and screen-replay simulations), miners generate variations using diffusion models and validate identity preservation locally, and validators grade submissions through an external API combined with reputation scoring. Miners encrypt submissions with drand timelock until grading is ready, then upload to S3. The entire cycle—query, generate, grade, reward—takes approximately one hour per validator cycle.
Auto-generated from the GitHub repository and may not reflect the latest changes.
Yanez is a Bittensor subnet focused on identity-preserving face image variations for KYC and fraud-detection research. Miners generate synthetic face variations (background changes, lighting/expression/pose edits, and screen-replay simulations) using diffusion models, while validators evaluate submission quality through automated pre-checks, identity preservation validation, and manual review. The subnet incentivizes high-quality adversarial face data to help financial institutions and researchers improve biometric fraud detection and presentation-attack resistance.
Yanez operates as a request-response cycle between validators and miners on the Bittensor subnet. Validators download base face images from the Yanez API, build a standardized 6-variation challenge (background_in/out, 3 combined edits, screen_replay) with a drand timelock target, and query a random sample of miners in batches (~150 miners per batch). Miners receive image requests, generate variations using FLUX (or alternative diffusion models), validate identity preservation locally (AdaFace ≥0.7), encrypt with drand timelock, upload encrypted images to S3, and return S3 submission references.
After the drand timelock expires (~40 minutes), validators call the external grading API to score submissions on KAV (image quality + identity). Validators combine KAV (10%) with UAV reputation (90%) from post-validation review, calculate blended exponential-decay rewards for top performers, and set weights on-chain. Unqueried miners still receive UAV-only rewards from reputation snapshots; new miners without snapshots receive KAV only.
Voice clone requests follow the same encrypt/upload/submit path but are UAV post-graded only. The entire forward pass takes ~1 hour per validator.
Phase 5 Cycle 1 Execution (Oct 19 – Nov 19, 2026): Miners generate 6 synthetic face variations per challenge (background_in, background_out, 3 combined edits, screen_replay) and optionally a voice clone. Live KAV samples one face variation per round and grades it on validation score + identity preservation (≥0.6 threshold for top 50). Screen replay and voice feed UAV post-grading only.
UAV prediction scores accumulate from manual review: face variations scored out of 25 (5 images × 5 pts each), screen replay out of 6 (6 pts if breaks PL v3 + correct cues/device/identity; 3 pts if identity preserved but no PL break), voice out of 5 (5 pts if tokens match + SpeechBrain identity ≥0.6; 3 pts if identity preserved with minor token mismatches). Finalized UAV from previous cycle (Phase 4, Cycle 5) is distributed during Execution. Effective data-gen miner take: ~16.5% of total emissions (up from ~14.35%).
The sections above were auto-generated from the GitHub repository and may not reflect the latest changes. View repository (github.com, opens in a new tab, external site)
Yanez SN54 generates synthetic identities for challenging Yanez humanhood, presence, and uniqueness detection models.
SN54 powers Yanez. Yanez is the infrastructure for Human Uniqueness. Turning what makes every person one-of-a-kind into their strongest layer of trust and integrity. Effective human detection requires models that can discern a real human from a synthetic one, models that can prove that a human is present, not an injection pretending to be the actual human, and models that can ensure that every human can be uniquely identified, so no one can hold multiple identities.
This information was auto-extracted from the GitHub repository and may be incomplete or out of date. Always refer to the subnet's GitHub repository (github.com, opens in a new tab, external site) for the latest instructions.
Sources disagree: GPU, VRAM, Storage
Not yet verified: Notes
Sources disagree: RAM, Recommended RAM, Storage
Not yet verified: Notes
Machine-extracted from the subnet's repository docs; may be wrong or out of date. Check the repository before buying or renting hardware. Open the repository (github.com, opens in a new tab, external site) · Extracted 2 Nov 2026
Clone the Yanez repository
git clone https://github.com/yanez-compliance/MIID-subnet.git && cd MIID-subnet
Run automated setup script (installs system packages, Python venv, image-generation dependencies, AdaFace). Alternative: follow Option 2 manual steps.
bash scripts/miner/setup.sh
Activate the Python virtual environment (do this every time you open a new terminal)
source miner_env/bin/activate
Set Hugging Face token and GPU device before first miner run. Create token at huggingface.co/settings/tokens and accept model licenses (FLUX.2-klein-4B, FLUX.1-Kontext-dev)
export HF_TOKEN="hf_YOUR_TOKEN_HERE" && export FLUX_DEVICE="cuda"
Create a Bittensor wallet (skip if you already have a registered miner)(optional)
btcli wallet create --wallet.name miner_wallet --wallet.hotkey miner_hotkey
Register miner to the subnet (requires TAO; skip if already registered). For first-time setup, use testnet (netuid 322) first.(optional)
btcli subnet register --netuid 54 --wallet.name miner_wallet --wallet.hotkey miner_hotkey --subtensor.network finney
Start the miner. Verify 'Phase 4 image generation: ENABLED' in logs. If disabled, run 'pip install -r requirements-miner.txt' and complete AdaFace setup.
python neurons/miner.py --netuid 54 --subtensor.network finney --subtensor.chain_endpoint wss://entrypoint-finney.opentensor.ai:443 --wallet.name miner_wallet --wallet.hotkey miner_hotkey --logging.debug
Clone the Yanez repository
git clone https://github.com/yanez-compliance/MIID-subnet.git && cd MIID-subnet
Run automated setup script (installs system dependencies, creates Python venv, installs requirements). Alternative: follow Option 2 manual steps.
bash scripts/validator/setup.sh
Activate the Python virtual environment
source validator_env/bin/activate
Stake TAO to the subnet (amount shown is example; adjust as needed)
btcli stake add --netuid 54 --amount 100 --wallet.name your_wallet_name --wallet.hotkey your_hotkey --subtensor.network finney
Start the validator. It will download base images, reset Phase 4 cycle state, and begin forward passes (~1 hour per pass: batch queries, 40-min drand wait, grading, weight setting).
python neurons/validator.py --netuid 54 --wallet.name your_wallet_name --wallet.hotkey your_hotkey --subtensor.network finney
| Day (UTC) | Share |
|---|---|
| 2026-11-06 | 0.16% |
| 2026-11-05 | 0.12% |
| 2026-11-04 | 0.12% |
| 2026-11-03 | 0.12% |
| 2026-11-02 | 0.11% |
| 2026-11-01 | 0.09% |
| 2026-10-31 | 0.08% |
| 2026-10-30 | 0.08% |
| 2026-10-29 | 0.09% |
| 2026-10-28 | 0.09% |
| 2026-10-27 | 0.03% |
| 2026-10-26 | 0.02% |
| 2026-10-25 | 0.03% |
| 2026-10-24 | 0.03% |
| 2026-10-23 | 0.03% |
| 2026-10-22 | 0.03% |
| 2026-10-21 | 0.03% |
| 2026-10-20 | 0.04% |
| 2026-10-19 | 0.05% |
| 2026-10-18 | 0.05% |
| 2026-10-17 | 0.05% |
| 2026-10-16 | 0.06% |
| 2026-10-15 | 0.07% |
| 2026-10-14 | 0.08% |
| 2026-10-13 | 0.07% |
| 2026-10-12 | 0.07% |
| 2026-10-11 | 0.07% |
| 2026-10-10 | 0.07% |
| 2026-10-09 | 0.07% |
| 2026-10-08 | 0.07% |
| 2026-10-07 | 0.07% |
| 2026-10-06 | 0.08% |
| 2026-10-05 | 0.09% |
| 2026-10-04 | 0.08% |
| 2026-10-03 | 0.08% |
| 2026-10-02 | 0.08% |
| 2026-10-01 | 0.06% |
| 2026-09-30 | 0.06% |
| 2026-09-29 | 0.05% |
| 2026-09-28 | 0.05% |
| 2026-09-27 | 0.07% |
| 2026-09-26 | 0.10% |
| 2026-09-25 | 0.02% |
| 2026-09-24 | 0.06% |
| 2026-09-23 | 0.05% |
| 2026-09-22 | 0.05% |
| 2026-09-21 | 0.05% |
| 2026-09-20 | 0.04% |
| 2026-09-19 | 0.04% |
| 2026-09-18 | 0.04% |
| 2026-09-17 | 0.04% |
| 2026-09-16 | 0.06% |
| 2026-09-15 | 0.05% |
| 2026-09-14 | 0.04% |
| 2026-09-13 | 0.03% |
| 2026-09-12 | 0.02% |
| 2026-09-11 | 0.02% |
| 2026-09-10 | 0.02% |
| 2026-09-09 | 0.02% |
| 2026-09-08 | 0.03% |
| 2026-09-07 | 0.03% |
| 2026-09-06 | 0.03% |
| 2026-09-05 | 0.02% |
| 2026-09-04 | 0.02% |
| 2026-09-03 | 0.02% |
| 2026-09-02 | 0.02% |
| 2026-09-01 | 0.01% |
| 2026-08-31 | 0.02% |
| 2026-08-30 | 0.02% |
| 2026-08-29 | 0.02% |
| 2026-08-28 | 0.03% |
| 2026-08-27 | 0.02% |
| 2026-08-26 | 0.03% |
| 2026-08-25 | 0.03% |
| 2026-08-24 | 0.04% |
| 2026-08-23 | 0.04% |
| 2026-08-22 | 0.04% |
| 2026-08-21 | 0.05% |
| 2026-08-20 | 0.04% |
| 2026-08-19 | 0.04% |
| 2026-08-18 | 0.03% |
| 2026-08-17 | 0.03% |
| 2026-08-16 | 0.03% |
| 2026-08-15 | 0.03% |
| 2026-08-14 | 0.03% |
| 2026-08-13 | 0.03% |
| 2026-08-12 | 0.03% |
| 2026-08-11 | 0.04% |
| 2026-08-10 | 0.05% |
| 2026-08-09 | 0.06% |