开源红队工具助力图像模型安全测试
What AI Safety needs is better tooling and engineering.
What AI Safety needs is better tooling and engineering.
AI 安全需要更好的工具和工程。
For instance, building stronger red-teaming tools.
例如，构建更强大的红队测试工具。
Great to see this open-source effort to red-team image models. It seems to learn better ways to write attack prompts.
很高兴看到这一针对图像模型进行红队测试的开源努力。它似乎能学习到编写攻击提示词更好方法。
It is open source and runs on an open Qwen model with Gemini Flash as the judge, so defenders can run the same tests on their own image models.
它是开源的，并在开放的 Qwen 模型上运行，以 Gemini Flash 作为评判者，因此防御方可以在自己的图像模型上运行相同的测试。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力