4 papers · 1 filter
VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models
Ravikumar Balakrishnan, Mansi Phute
As Vision Language Models (VLMs) are deployed across safety-critical applications, understanding and controlling their behavioral patterns has become increasingly important. Existi…
VISOR: Visual Input-based Steering for Output Redirection in Vision-Language Models
Mansi Phute, Ravikumar Balakrishnan
Vision Language Models (VLMs) are increasingly being used in a broad range of applications, bringing their security and behavioral control to the forefront. While existing approach…
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…
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…