AVEC is a proposed framework for per-query differential privacy budgeting, entity-level randomized response, and hash-based verification when delegating LLM queries to a remote model.
Scalm: Towards semantic caching for automated chat services with large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AVEC: Bootstrapping Privacy for Local LLMs
AVEC is a proposed framework for per-query differential privacy budgeting, entity-level randomized response, and hash-based verification when delegating LLM queries to a remote model.