Cisco research demonstrates VLMs can be manipulated by imperceptible pixel perturbations embedding instructions in images (e.g., banners/previews), creating a covert channel that humans and simple filters miss.

Cisco research demonstrates VLMs can be manipulated by imperceptible pixel perturbations embedding instructions in images (e.g., banners/previews), creating a covert channel that humans and simple filters miss.

Part of the PlainSec briefing for 2026-05-07

Sources

SecurityWeek

Cisco research demonstrates VLMs can be manipulated by imperceptible pixel perturbations embedding instructions in images (e.g., banners/previews), creating a covert channel that humans and simple filters miss.Cisco research demonstrates VLMs can be manipulated by imperceptible pixel perturbations embedding instructions in images (e.g., banners/previews), creating a covert channel that humans and simple filters miss.Part of the PlainSec briefing for 2026-05-07Sources