{"slug": "white-circle-open-sources-rise-after-finding-image-model-safeguards-still-fail", "title": "White Circle open-sources RISE after finding image-model safeguards still fail", "summary": "White Circle, a Paris-based AI safety company, has open-sourced RISE, a red-teaming system that searches for reusable ways to bypass image-generator safeguards, after reporting a 13.3% human-verified attack rate on DALL·E 3 and higher rates on two newer image models from OpenAI and Google DeepMind. The company's announcement on X calls for independent third-party monitoring of AI models, and White Circle says its results show a public, non-frontier model can probe commercial image safeguards.", "body_md": "# White Circle open-sources RISE after finding image-model safeguards still fail\n\n**The Paris-based AI safety company reports a 13.3% human-verified attack rate on DALL·E 3 and higher rates on two newer image models.**\n\n        By [Ryan Merket](https://runtimewire.com/author/ryan-merket)\n        · Published \n\nPrimary source: [X](https://x.com/whitecircle/status/2110420697814114693)\n\n## Why it matters\n\nRISE makes the measurement problem in AI red-teaming concrete: attack rates depend on what counts as a violation and how the judge is calibrated. White Circle's results also show that a public, non-frontier model can probe commercial image safeguards, strengthening the case for independent evaluation while leaving open how outside testers will gain durable access and independence.\n\n[White Circle](https://whitecircle.com/) has open-sourced RISE, a red-teaming system that searches for reusable ways to get image generators past their safeguards. The company says its tests found human-confirmed prohibited images on DALL·E 3 and newer models from OpenAI and Google DeepMind. Its [announcement on X](https://x.com/whitecircle/status/2110420697814114693) calls for independent third-party monitoring of AI models.", "url": "https://wpnews.pro/news/white-circle-open-sources-rise-after-finding-image-model-safeguards-still-fail", "canonical_source": "https://runtimewire.com/article/white-circle-rise-image-model-red-teaming", "published_at": "2026-10-14 18:00:18+00:00", "updated_at": "2026-10-15 00:10:46.950113+00:00", "lang": "en", "topics": ["ai-safety", "generative-ai", "computer-vision", "ai-research"], "entities": ["White Circle", "RISE", "DALL·E 3", "OpenAI", "Google DeepMind"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/white-circle-open-sources-rise-after-finding-image-model-safeguards-still-fail", "markdown": "https://wpnews.pro/news/white-circle-open-sources-rise-after-finding-image-model-safeguards-still-fail.md", "text": "https://wpnews.pro/news/white-circle-open-sources-rise-after-finding-image-model-safeguards-still-fail.txt", "jsonld": "https://wpnews.pro/news/white-circle-open-sources-rise-after-finding-image-model-safeguards-still-fail.jsonld"}}