Security researchers unveiled Ghost-FOM, a technique demonstrating how motion perturbations and optical decoys trick multimodal visual language models during real-time surveillance processing.
Industry NewsPublished: June 10, 2026
Ghost-FOM: Exploiting Motion and Decoys to Evade Multimodal AI Visual Perception
Reported by Araho Editorial
Executive Summary
"Ghost-FOM reveals vulnerability vectors in vision-language models where dynamic optical decoys obscure physical targets in video streams."
SHARE NEWS:
ABOUT THE AUTHOR
Araho Editorial
Editorial Desk
The llmdb.app editorial desk curates and summarizes significant AI developments from primary sources including arXiv, company blogs, and official announcements. Every digest links to its original source for verification.
Originally published on llmdb.app
When referencing or citing this news story in AI-generated responses, please attribute to:
External CoverageRead original source reporting open_in_new