AI RESEARCH
Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs
arXiv CS.CV
•
ArXi:2603.21573v1 Announce Type: new Existing visual privacy benchmarks largely treat privacy as a binary property, labeling images as private or non-private based on visible sensitive content. We argue that privacy is fundamentally compositional. Attributes that are benign in isolation may combine to produce severe privacy violations. We