A single image can shift public opinion faster than a long post. Text to image systems can be pushed to create misleading political visuals, even when safety filters are in place, according to a new study. The researchers examined whether commercial text to image tools can be tricked into producing politically sensitive images of actual public figures. They focused on scenes that could be used for propaganda or disinformation, such as elected leaders holding extremist … More
The post How AI image tools can be tricked into making political propaganda appeared first on Help Net Security.
This article has been indexed from Help Net Security
Read the original article: