Teemo retweeted
Introducing Primus Confidential Finance (dapp.primuslabs.xyz), where privacy meets transfer and yield on-chain.
We're excited to announce a collaboration between Primus @primus_labs, Unitas @UnitasLabs, and United Stables @UTechStables to launch a Confidential Finance Product on @BNBCHAIN, powered by the Fully Homomorphic Encryption (FHE) technique.
This isn't just another confidential transfer or on-chain vault. It's a new standard for how private, compliant, and capital-efficient on-chain finance can work. 🧵
现在这些项目方一直强调不知道咋说了
🍞 Bread 早期访问队列已经超过 10,000 人!虽然项目方说参与主网也没有奖励,但是还是那个但是
由 @0xMiden 强力驱动。
隐私不是附加功能,而是从一开始就融入其中。
现在就加入队列 👉 miden.xyz/bread
🍞 Bread 早期访问队列已经超过 10,000 人!虽然项目方说参与主网也没有奖励,但是还是那个但是
由 @0xMiden 强力驱动。
隐私不是附加功能,而是从一开始就融入其中。
现在就加入队列 👉 miden.xyz/bread
为什么模型指纹排行榜要看三个分数?
训练一个好模型要花大量钱和时间,但复制、微调、蒸馏只需要几分钟。一旦模型被二次加工,原来的“血统”几乎就断了——你很难再证明它最初是谁训练的。
对于开源权重模型来说,这是个现实问题。如果你想在模型被别人拿去微调、蒸馏之后,依然能可靠地证明“这是我的模型”,就需要给模型嵌入指纹(fingerprinting)。
Sentient Foundation 为此做了一个公开的模型指纹排行榜(fingerprint.sentient.foundat…),专门评估各种指纹方案。他们用三个维度来打分,而不是只看一个指标:
1. Retention / Utility(保留性)
嵌入指纹后,模型的正常能力会下降多少。理想情况是几乎不影响原有表现。
2. Robustness
面对专门设计的移除攻击时,指纹还能不能留下来。有些方案在普通微调下还行,但一遇到针对性攻击就失效了。
3. Verification(验证性)
模型所有者能否稳定地从疑似模型里读出指纹,并完成所有权证明。验证不可靠的话,即使指纹还在也意义不大。
这三个维度是相互制衡的。有的方案鲁棒性很高,但会明显拉低模型能力;有的几乎不影响性能,却很容易被攻击掉。排行榜把这些权衡公开出来,让人能更清楚地看到不同方案的实际水平。
目前排行榜上评估了十余种方案,包括来自不同研究团队的方法。Sentient 自己此前提出的 Perinucleus 方案(NeurIPS 2025 Spotlight)曾展示过在 Llama-3.1-8B 上嵌入上万条指纹且性能损失较小的结果,相关工作也影响了这个排行榜的设计。
同时他们还开源了评估框架 mlprints,方便研究者统一实现指纹方案、攻击方法和验证流程,并把新方案提交到排行榜上测试。
开源模型的所有权证明,目前还没有被完美解决的方案。这个排行榜的价值在于,它把“指纹到底能不能用”这件事从论文里的自报数据,变成了可公开比较、可复现的基准。
排行榜地址:fingerprint.sentient.foundat…
Why are there three leaderboard scores?
Model provenance carries clues about the history, training data, development process, and later modifications. Fine-tuning and distillation obscure provenance to the point where it’s virtually impossible to track the origin of the model back to its creator.
And if you as an owner want to reliably prove attribution and claim ownership of your open weights, you should choose a fingerprinting scheme based on these three dimensions:
>> Retention: whether the fingerprint is detectable without sacrificing normal model quality.
In other words, how embedding fingerprints affects model performance compared to the unfingerprinted model's nominal performance.
>> Robustness: whether the fixed attack can remove the fingerprint, preserving output quality.
In other words, how resistant the fingerprinted model is to malicious attempts to obscure its origin.
>> Verification: whether model owner/creator can reliably read the fingerprint back from a suspected copy and verify his IP property.
In other words, how reliable model attribution would be under scrutiny/inspection.




































