White Circle Red-Teaming Finds OpenAI and Google Image Models Easily Jailbroken to Produce Explicit Content
AI safety firm White Circle developed an automated attack method called RISE, using off-the-shelf models, that bypassed safety filters on DALL·E 3, GPT-Image-2, and Google's Nano Banana 2 about 13 percent of the time to...
Risk:
[+0.01 pp]
AGI:
—