Skip to content
Research

Physiognomy Revisited: How Vision-Language Models Encode Sensitive Attributes Through Image Transformation.

arXiv:2610.35910v1 Announce Type: cross Abstract: Emergent generative AI technologies, while remarkably beneficial across several tasks and domains, can suffer from unforeseen vulnerabilities and difficult-to-anticipate failure modes. Such failure modes can di

arXiv cs.AIResearch source·