arXiv (All)
open access
Contrastive Privacy: A Semantic Approach to Measuring Privacy of AI-based Sanitization
AI-based sanitization can remove concepts from images and text, but privacy evaluation remains largely ad hoc. We propose contrastive privacy, a formal definition that yields a quantitative test with a semantic interpretation. Under formal assumptions, we derive a conditional sufficiency result for
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Don't Send What You Don't Need: Question-Guided Token Pruning as a Privacy Defense for Vision-Language Models#1109649
- Robustness of Vision Language Models Against Split-Image Harmful Input Attacks#798765
- Robustness of Vision Language Models Against Split-Image Harmful Input Attacks#797351
- The Interpretation of Classically Quantified Sentences: A set-theoretic approach#78420
- Contrastivity and indistinguishability#754850
Record · ID 1013559
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive