Counterfactual Neighborhood Risk Fields: Evidence-Grounded Selective Safety for Vision-Language Models

arXiv cs.AIOctober 16, 2026en

arXiv cs.AI

AI Global Wire

arXiv:2610.20679v1 Announce Type: new Abstract: Representation-based safety defenses for vision-language models (VLMs) often learn to separate harmful from benign inputs, but separation alone does not establish what a risk score means or when it should be trusted. We introduce Counterfactual Neighborhood Risk Fields (CNRF), an evidence-grounded framework for selective VLM safety. CNRF constructs context-matched benign-harmful counterfactual pairs, uses their representation differences as capability-related risk directions, and estimates neighborhood support separately from risk. This separation prevents unfamiliarity from being conflated with harmfulness and enables selective intervention ra

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Verktyg
• Forskning