DAMPER learns domain privacy prototypes via contrastive learning and uses them to guide mask-free privacy extraction, preference-aligned rewriting, and differential privacy sampling for LLMs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Mask-Free Privacy Extraction and Rewriting: A Domain-Aware Approach via Prototype Learning
DAMPER learns domain privacy prototypes via contrastive learning and uses them to guide mask-free privacy extraction, preference-aligned rewriting, and differential privacy sampling for LLMs.