• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
AI
Report

Sentient Foundation releases a leaderboard for testing AI model fingerprints

A post says the leaderboard ranks submitted ownership marks by verification reliability, resistance to removal and impact on model skill.

2 Sources, 1h ago, first seen 1h ago

TLDR

A post says Sentient Foundation released its free, open-source Fingerprinting Leaderboard and the mlprints test code. Researchers submit ways to hide ownership marks in AI models; Sentient embeds them in test models, tries to strip them out and ranks how reliably they can be verified, how well they resist removal and their impact on model skill. The post says Sentient’s Perinucleus method embedded 24,576 fingerprints in Llama-3.1-8B without degrading utility; they survived standard fine-tuning.

Combined views

—

2 Sources, first seen 1h ago

— likes— comments— saves— reposts

Combined views

—

2 Sources, first seen 1h ago

— likes— comments— saves— reposts
Image: @rohanpaul_ai on X

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Featured Source

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

2 Sources

Rohan Paul@rohanpaul_aiGood news for anyone trying to prove a model is theirs. Sentient Foundation released the Fingerprinting Leaderboard, a free, open source benchmark that tests fingerprinting methods, meant to prove an AI model was copied from yours. Researchers submit a method for hiding an ownership mark inside a model, and Sentient puts that mark into its own test models, tries to strip it out, then ranks the method on a public website. The code that runs these tests, called mlprints, is released too. A fingerprint trains a model to return unlikely answers to secret prompts, so an owner can test a suspected copy through its API alone. But a fingerprint that survives every attack is still useless if the owner can’t read it back reliably. Sentient Foundation’s Fingerprinting Leaderboard scores that verification step directly, alongside how well the mark resists removal and how much model skill it costs. Sentient’s Perinucleus method embedded 24,576 fingerprints in Llama-3.1-8B without degrading utility, is also competing on the leaderboard, and the fingerprints survived standard fine-tuning.1h
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI

    2 Sources

    Rohan Paul@rohanpaul_aiGood news for anyone trying to prove a model is theirs. Sentient Foundation released the Fingerprinting Leaderboard, a free, open source benchmark that tests fingerprinting methods, meant to prove an AI model was copied from yours. Researchers submit a method for hiding an ownership mark inside a model, and Sentient puts that mark into its own test models, tries to strip it out, then ranks the method on a public website. The code that runs these tests, called mlprints, is released too. A fingerprint trains a model to return unlikely answers to secret prompts, so an owner can test a suspected copy through its API alone. But a fingerprint that survives every attack is still useless if the owner can’t read it back reliably. Sentient Foundation’s Fingerprinting Leaderboard scores that verification step directly, alongside how well the mark resists removal and how much model skill it costs. Sentient’s Perinucleus method embedded 24,576 fingerprints in Llama-3.1-8B without degrading utility, is also competing on the leaderboard, and the fingerprints survived standard fine-tuning.1h
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet