LATIDIA · Ciberseguridad

BodhiPromptShield: mediación previa a la interferencia para la propagación de la privacidad de forma superficial en las canalizaciones de agentes de LLM

arXiv:2604.05793v2 Announce Type: replace Abstract: In LLM agent pipelines, prompt privacy risk propagates beyond a single model call: raw user content enters retrieval queries, memory write, tool arguments, OCR-derived

La noticia

arXiv:2604.05793v2 Announce Type: replace Abstract: In LLM agent pipelines, prompt privacy risk propagates beyond a single model call: raw user content enters retrieval queries, memory writes, tool arguments, OCR-derived text, and logs, and every downstream copy inherits what the first write contained. Existing de-identification pipelines protect document boundaries but not this cross-stage surface. We present BodhiPromptShield, a policy-aware mediation layer that detects sensitive spans before they propagate, replaces each with a typed placeholder, a semantic abstraction, or a secure symbolic token under a configured policy, and defers restoration to authorized execution boundaries. We evaluate it under one protocol against Presidio, Casper-style sanitization, an LLM sanitizer, and transformer and learned detectors,