Rohan Paul· @rohanpaul_ai · X·· 3 小时前AI 评分55
AI 导读
White Circle 开源了 RISE，一个自动化红队测试算法，用于检测 AI 图像生成器能否被诱导生成其规则禁止的图片。RISE 无需额外训练，底层使用 Qwen、Gemini Flash 等公开模型，通过搜索攻击策略并按通过率给予策略反馈，即使面对几乎全部拦截的模型也能持续学习；防守方可立即用自己的图像模型运行它。
正文
Good safety work increasingly means good search.
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.
That keeps the search learning even against models that block almost everything.
The code is open, the models it uses are public, and defenders can run it on their own image models today.
We are open-sourcing RISE, our red-teaming algorithm that breaks the safeguards of the latest image models from OpenAI, DeepMind, and others. RISE uses readily available models like Qwen and Gemini Flash under the hood, with no additional training required. Read more: https://whitecircle.com/research/breaking-frontier-image-models在 X 查看被引用的帖子
来源：Rohan Paul · x.com