Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
One Perturbation, Two Failure Modes: Probing VLM Safety via Embedding-Guided Typographic Perturbations
Ravikumar Balakrishnan, Sanket Mendapara
Typographic prompt injection exploits vision language models' (VLMs) ability to read text rendered in images, posing a growing threat as VLMs power autonomous agents. Prior work ty…
cs.CV2026
Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models
Ravikumar Balakrishnan, Sanket Mendapara, Ankit Garg
We study typographic prompt injection attacks on vision-language models (VLMs), where adversarial text is rendered as images to bypass safety mechanisms, posing a growing threat as…