White Circle发布RISE自动化AI图像安全测试工具
Good safety work increasingly means good search.
Good safety work increasingly means good search.
良好的安全工作日益意味着良好的搜索能力。
White Circle’s released RISE, an automated tool for testing whether AI image generators can be tricked into making pictures their own rules forbid. It searches over attack strategies for image models. An open attacker model turns each strategy into many prompts, and the strategy gets credit for how many of them get through.
White Circle 发布了 RISE，这是一个自动化工具，用于测试 AI 图像生成器是否能被诱骗去生成其自身规则所禁止的图片。 它针对图像模型的攻击策略进行搜索。一个公开的攻击者模型会将每种策略转化为多个提示词（prompts），并根据其中有多少个成功绕过限制来给该策略计分。
That keeps the search learning even against models that block almost everything.
这使得搜索学习即使在面对几乎屏蔽所有内容的模型时也能持续进行。
The code is open, the models it uses are public, and defenders can run it on their own image models today.
代码是开源的，所使用的模型也是公开的，防御者今天就可以在自己的图像模型上运行它。
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