Model-Based Detection

Model-Based Detection is an automated security feature in Human Passport that evaluates whether Ethereum addresses are controlled by humans or bots (Sybil entities) — without requiring any user interaction.

What it does

The system analyzes historical transaction data from an Ethereum address and assigns a score between 0 and 100. Higher scores indicate stronger signals of human activity, while lower scores may flag an address for additional verification.

Why it matters

• Sybil resistance — protects dApps and programs from automated abuse.
• Frictionless experience — active users can be evaluated automatically, with no extra steps.
• Fallback paths — users with low scores can still earn Passport stamps as an alternative way to verify their humanity.

In this section

• Guide to Model-Based Detection — a deeper look at how the ETH Activity Model works, which networks it covers, and how scores influence access across the dApp ecosystem.