Researchers Show How AI Image Downscaling Can be an Attack Vector. Researchers discovered a method to embed invisible prompt injections that are activated during AI’s processing of an image. When the model scales down these images, the hidden malicious instructions allow theft of data from popular image production systems.
First seen on govinfosecurity.com
Jump to article: www.govinfosecurity.com/ai-models-resize-photos-open-door-to-hacking-a-29276
