A learned stochastic embedding obfuscator, the Stained Glass Transform, is claimed to reduce mutual information between prompts and their server-side representations while preserving LLM utility.
Large language models for code completion: A systematic literature review,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Obfuscations Of LLM Embedding Sequences: Stained Glass Transform
A learned stochastic embedding obfuscator, the Stained Glass Transform, is claimed to reduce mutual information between prompts and their server-side representations while preserving LLM utility.