Jinsong Wu
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Research Timeline
2026
BodhiPromptShield: Pre-Inference Prompt Mediation for Suppressing Privacy Propagation in LLM/VLM Agents
BodhiPromptShield is a policy-aware framework that mediates prompt privacy by detecting sensitive data and replacing it with secure placeholders across multiple stages (retrieval, memory, tools) to prevent privacy leakage in LLM/VLM agents.
Highlighted terms show continued research focus across papers