Counterfactual Neighborhood Risk Fields: Evidence-Grounded Selective Safety for Vision-Language Models
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...
Read more: https://arxiv.org/abs/2610.20679
Scan with your phone
Scan with your phone