arXiv:2610.09240v1 Announce Type: new Abstract: Modern web agents built on large vision-language models process webpages, select relevant UI elements, and translate model outputs into browser actions. Existing visual red-teaming approaches use adversarial visual content to manipulate this process. However, they primarily target model inference and do not explicitly account for structured input processing or action post-processing.

Read the full article at arXiv cs.CR →