Assessing Visual Privacy Risks in Multimodal AI: A Novel Taxonomy-Grounded Evaluation of Vision-Language Models

Documenti analoghi

• Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs
  di: Tsaprazlis, Efthymios, et al.
  Pubblicazione: (2026)
• VoxGuard: Evaluating User and Attribute Privacy in Speech via Membership Inference Attacks
  di: Tsaprazlis, Efthymios, et al.
  Pubblicazione: (2025)
• Can Text-to-image Model Assist Multi-modal Learning for Visual Recognition with Visual Modality Missing?
  di: Feng, Tiantian, et al.
  Pubblicazione: (2024)
• Taxonomy-Aware Evaluation of Vision-Language Models
  di: Snæbjarnarson, Vésteinn, et al.
  Pubblicazione: (2025)
• Assessing Privacy Preservation and Utility in Online Vision-Language Models
  di: Chaudhari, Karmesh Siddharam, et al.
  Pubblicazione: (2026)