BodhiPromptShield reduces stage-wise privacy propagation in LLM/VLM agents from 10.7% to 7.1% on the Controlled Prompt-Privacy Benchmark by mediating sensitive spans before inference and restoring only at authorized boundaries.
The algorithmic foundations of differential privacy,
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
-
BodhiPromptShield: Pre-Inference Prompt Mediation for Suppressing Privacy Propagation in LLM/VLM Agents
BodhiPromptShield reduces stage-wise privacy propagation in LLM/VLM agents from 10.7% to 7.1% on the Controlled Prompt-Privacy Benchmark by mediating sensitive spans before inference and restoring only at authorized boundaries.