AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Scale-Induced Semantic Shift in Visual Prompt Injection Against VLMs and Web Agents

arXiv · AI, language, vision and robotics · article · Nov 12, 2026 · UTC

Visual content in multimedia systems may be resized, compressed, or re-rendered before it is interpreted by a vision-language model. We study a security failure mode in which these transformations change the machine-readable semantics of an image: a textual instruction is not recovered at a $512\times512$ presentation resolution under our evaluation protocol but becomes recoverable after aggressive downsampling. We formulate this behavior as Scale-Induced Semantic Shift (SISS) and develop a closed-loop black-box framework that combines dual-scale verification, selective self-hardening, shallow

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-11-13T16:53:25.588Z. This is not the publication date.