White Circle open sources RISE, a red teaming method it says broke the safeguards of image models from OpenAI and Google
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:
Context
If off the shelf models can reliably push frontier image generators into producing banned images, safety filters at the biggest labs may be weaker than they look.
White Circle is an AI safety company, and this is its own research announcement. Its write up says RISE uses an older open source Qwen3 model as the attacker, an off the shelf Gemini Flash model as the judge and a lightweight harness, with no specialized models at any stage. The post reached the tracked feed through a repost by AK and a quote by kimmonismus.
Deep dive
On October 14, White Circle announced it is open sourcing RISE, its red teaming algorithm that breaks the safeguards of the latest image models from OpenAI, DeepMind and others, using readily available models like Qwen and Gemini Flash with no additional training.
According to White Circle's write up, RISE was tested on OpenAI's DALL·E 3 and GPT Image 2 and Google's Nano Banana 2, and produced images the platforms' own policies prohibit on up to 13% of its attempts. After the paper was submitted, OpenAI released GPT Image 2.5 Flare and Google released Nano Banana 2.1. White Circle says it ran RISE against both without changes, and that on explicit nudity its success rate more than doubled compared with the models they replaced.
The company says it shared its findings with the affected companies before publication. It has open sourced the reproduction pipeline on GitHub so defenders and regulators can test their own deployments, but is keeping the attack prompts, the strategies RISE found and the generated images private.
The write up also makes a policy argument. White Circle says labs are failing at safety and security, that self assessment will not fix it, and that governments should require independent third party monitoring of deployed models. It notes that 34 signatories at this month's UN General Assembly called for mandatory pre deployment testing, and that the United States, China, the United Kingdom and France have not signed.
The success rates are White Circle's own results; the company says it will present RISE at NeurIPS 2026.
What to expect next
Watch for responses from OpenAI and Google on whether they have patched the weaknesses White Circle reported, and whether independent researchers reproduce the success rates using the open source pipeline.
Also watch the policy push for mandatory third party testing, including whether any of the four countries White Circle names sign the UN call, and how RISE is received when it is presented at NeurIPS 2026.