Rohan Paul (@rohanpaul_ai) · 2026/10/14 23:13:58
Sentient Foundation 开源模型指纹基准：验证所有权标记抗移除性与读取可靠性
Sentient Foundation 发布免费开源的“模型指纹排行榜”（Fingerprinting Leaderboard），旨在标准化评估用于证明模型所有权的指纹技术。该基准不仅测试指纹在微调、蒸馏等攻击下的抗移除能力，还重点评估所有者通过 API 可靠读取指纹的能力及其对模型性能的损耗。配套代码 mlprints 已开源，其自研 Perinucleus 方法在 Llama-3.1-8B 中嵌入近 2.5 万个指纹且未显著降低效用，正参与榜单竞争。
报道全文原始报道全文
Rohan Paul (@rohanpaul_ai) · 2026-10-14 15
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.
↳ 引用 @sentient_found (Sentient Foundation): Models cost millions to train and minutes to copy. Fine-tuning and distillation can erase where they came from.
Introducing the Fingerprinting Leaderboard, an open benchmark for model provenance — built so the proof lives in the weights, not the paperwork.
