Sentient 开源模型指纹排行榜，可验证模型是否被盗用复制
模型被抄难举证？Sentient 开源了这个指纹排行榜，谁的隐藏标记最抗删、最好验证，排名一目了然。
Sentient Foundation 发布开源基准 Fingerprinting Leaderboard，用于测试模型指纹方法能否证明一个模型是从你的模型复制而来。研究者提交在模型内隐藏所有权标记的方案，Sentient 将标记植入自家测试模型并尝试抹除，再按表现公开排名，配套测试代码 mlprints 一并开源。排行榜直接给验证环节打分：模型所有者仅凭 API 就能读回标记，同时衡量标记的抗移除能力和对模型能力的损耗。Sentient 自家的 Perinucleus 方法在 Llama-3.1-8B 中嵌入了 24,576 个指纹，模型能力未受影响，指纹在常规微调后依然存活。
Good 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.
