SOURCE-LINKED INTELLIGENCE

Transfer Safety Awareness for Cross-Modal Safety Drift in Multimodal Large Language Models

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Visual modality enhances the capabilities of multimodal large language models (MLLMs) but also introduces a safety concern: a benign textual query may convey harmful intent when grounded in a visual image. We term this cross-modal safety drift and our pilot studies show that the safety response rate for such requests is substantially lower than that for requests containing explicitly unsafe text. This paper aims to systematically study this issue. First, we conduct an empirical analysis to identify representative unsafe response patterns. Building on these, we interpret model representations a

Read original source ↗ Open in workspace

recordType

paper

region

Global