White Circle 开源图像模型红队工具 RISE，可绕过主流模型安全防护
一个开源的红队工具，用 Qwen 加 Gemini Flash 就能测试自家图像模型够不够安全，做安全评测的可以上手试试。
White Circle 开源了红队算法 RISE，用来自动测试图像生成模型的安全防护。RISE 底层用 Qwen 模型编写攻击提示词，用 Gemini Flash 作为评判，无需额外训练。测试结果显示它能突破 OpenAI 和 DeepMind 等公司的最新图像模型防护，防守方可以用同一套工具自测。
What AI Safety needs is better tooling and engineering. For instance, building stronger red-teaming tools. Great to see this open-source effort to red-team image models. It seems to learn better ways to write attack prompts. 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. White Circle @whitecircle 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: whitecircle.com/research/break… Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 7 🔄 2 ❤️ 9 👀 1314 📊 6 ⚡
