Reading, Not Manipulating: Leveraging Router Logits for Multimodal Safety in MoE Vision-Language Models

Excerpt

arXiv:2610.07774v1 Announce Type: new Abstract: Vision-language models (VLMs) face compositional safety risks where harmful intent emerges from the interaction between visual and textual inputs. As mixture-of-experts (MoE) VLMs become increasingly common, recent work has explored various safety interventions, including prompting, supervised fine-tuning, and routing-based expert steering. However, these methods show inconsistent improvements across models and evaluation distributions, and the int