FERRET trains models with sparsely released 1-bit random projections, bounding privacy by mutual information, and reports better perplexity and speed than DPSGD on five small LLMs.
The Algorithmic Foundations of Differential Privacy , vol- ume 9 of Foundations and Trends® in Theoretical Computer Science
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
FERRET: Private Deep Learning Faster And Better Than DPSGD
FERRET trains models with sparsely released 1-bit random projections, bounding privacy by mutual information, and reports better perplexity and speed than DPSGD on five small LLMs.