all AI news
AI Art Generators Can Be Fooled Into Making NSFW Images
IEEE Spectrum spectrum.ieee.org
Nonsense words can trick popular text-to-image generative AIs such as DALL-E 2 and Midjourney into producing pornographic, violent, and other questionable images. A new algorithm generates these commands to skirt around these AIs’ safety filters, in an effort to find ways to strengthen those safeguards in the future. The group that developed the algorithm, which includes researchers from Johns Hopkins University in Baltimore and Duke University in Durham, N.C., will detail their findings in May 2024 at the IEEE Symposium …
ai art ai art generators algorithm art dall dall-e dall-e 2 filters future generative generative-ai image images large language models making midjourney nsfw popular safeguards safety stable diffusion text text-to-image trick words