Video Manipulation Can Trick Frontier AI Models Into Harmful Robot Actions

Security team robocurve's CoRL study shows that manipulated video inputs can trick all frontier models into performing harmful robot actions, as models perceive altered content different from what humans see.

2026-11-07 ~ 2026-11-08 · 2 related posts

• Video tampering tricks all frontier models into harmful robot actions, CoRL study warns — johnvmcdonnell · 2026-11-07
• Perceptual attacks fool embodied AI: frontier models stab what they think is an apple — teortaxesTex · 2026-11-08