elvis· @omarsar0 · X·· 3 小时前AI 评分52
AI 导读
Elvis Saravia 认为 AI 安全需要更好的工具与工程，例如构建更强的红队工具。他引用 @whitecircle 的内容指出，RISE 是开源红队算法，可突破 OpenAI、DeepMind 等最新图像模型的防护，底层使用 Qwen 和 Gemini Flash 等现成模型且无需额外训练。他补充说，该工具开源并运行在开放的 Qwen 模型上、以 Gemini Flash 作为评判，防御方可在自己的图像模型上运行同样的测试。
正文
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.
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：elvis · x.com