DeepInvert uses unlabeled obfuscated embeddings to train an inversion model that recovers up to 73.5% of original tokens against ObfusLM, versus 26.2% for the previous best attack.
Information leakage in embedding models,
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
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
DeepInvert: Semi-Supervised Embedding Inversion Against Obfuscated Language Models
DeepInvert uses unlabeled obfuscated embeddings to train an inversion model that recovers up to 73.5% of original tokens against ObfusLM, versus 26.2% for the previous best attack.