Anthropic正在建立一个开源系统，根据星期二发表的一篇博客文章，这个叫做FlashProve的系统是用来提供研究者所谓的“可证明的推论”的 — — 一个密码学的证明，基本上是数学上的保证，即给定的输出来自特定的模型。 由用户确认他们得到的答案
类似加密的电子邮件签名，让收件人确认一个消息确实来自其声称的发送者，FlashProve会强力反对冒牌货试图将一个模型伪装成另一个模型，即使冒牌货是建造和运行模型的实验室。 研究人员特别指出，该系统可以被用来阻止AI公司以更便宜的模型进行秘密互换来削减成本，或者用更昂贵的模型来提升其性能结果。
FlashProve还可以用来验证第三方的声称，即某项具体任务是由高级模型完成的。 “一个开发者可能声称他们的软件库被前沿网络安全模型扫描了弱点，或者一个公司可能声称其业务计划得到了一个适当的模型，”研究人员写道。 “用户如何核查这些声称？”
为了发挥作用，该系统要求人工智能实验室公布其发布的每个模型的“指印”，这些指印日后可与具体输出物相匹配，并经过加密核实。 Anthropic和OpenAI等封闭模型制造者必须保密。 这意味着实验室可以公布指纹而不放弃他们最宝贵的资产，使系统也能与商业模型合作。 该系统也设计为轻量级，因此可以在本地设备上进行核查。
作为公告的一部分，研究人员发布为系统各要素提供了详细的技术规格和工作代码，在GitHub上的开源许可证下公开提供。 该系统的研究正在进行，没有计划在Anthropic或任何其他实验室部署。
“这个研究职位意在分享中期进展，而不是已完成的研究议程，”研究人员在公告中解释说。 “我们明确认同这一点，目标是让其他国家审视我们所做的工作，接受和改进我们的工作。”
本文由 AI图鉴自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
Anthropic is working on an open-source system to verify which AI model produced a given output, according to a blog post published Tuesday. The system, called FlashProve, is built to provide what researchers call “provable inference” – a cryptographic proof, essentially a mathematical guarantee, that a given output came from a specific model. It’s meant to let users confirm that the answer they received really came from the model they think they’re using.
Similar to cryptographic email signatures that let recipients confirm a message really came from its claimed sender, FlashProve would be robust against impostors attempting to disguise one model as another, even when the impostor is the lab that built and runs the model. In particular, the researchers note that the system could be used to prevent an AI company from secretly swapping in a cheaper model to cut costs, or a more expensive model to inflate its performance results.
FlashProve could also be used to verify claims by third parties that a specific task was done by an advanced model. “A developer might claim that their software library was scanned for vulnerabilities by a frontier cybersecurity model, or a company might claim that its business plan was given the go-ahead by an appropriate model,” the researchers write. “How can a user verify these claims?”
To work, the system requires AI labs to publish a “fingerprint” of each model they release that can later be matched to specific outputs and verified cryptographically. Crucially, the fingerprints don’t reveal a model’s weights, the internal numbers that define how it behaves and which closed-model makers like Anthropic and OpenAI keep private. That means labs could publish the fingerprints without giving up their most valuable asset, enabling the system to work with commercial models, too. The system is also designed to be lightweight, so verification could be performed on a local device.
As part of the announcement, researchers released a detailed technical specification and working code for various elements of the system, which is publicly available under an open-source license on GitHub. Research in the system is ongoing, and there are no plans to deploy it at Anthropic or any other lab.
“This research post is meant to share intermediate progress, and not a completed research agenda,” researchers explain in the announcement post. “We are sharing this explicitly with the goal that others look at what we have done, take it, and improve it.”
Auto-fetched and translated by AI Atlas. All rights belong to the original author.