Arman Zharmagambetov

@arreqe_ai

PhD. Researcher in AI/ML @ Meta FAIR (MSL)

following
followers

Tested image-based prompt attacks had at most 18% success with a realistic benign task present, team member says

A team member describes image-based prompt injection as less studied than text-based attacks. The evaluation covered existing methods targeting commercial vision-language models—AI systems that handle images and text.

2 Sources, 43d ago, first seen 43d ago

Featured in

Tested image-based prompt attacks had at most 18% success with a realistic benign task present, team member says

Featured in

Tested image-based prompt attacks had at most 18% success with a realistic benign task present, team member says