LATIDIA · Ciberseguridad

CIPL: un marco consciente del canal para la fuga de privacidad recuperable en agentes de LLM

arXiv:2609.21686v1 Anuncio Tipo: nuevo Resumen: La fuga de privacidad en los agentes LLM se evalúa comúnmente dentro de componentes individuales como memoria, recuperación o canalizaciones de uso de herramientas, lo que dificulta distinguir

La noticia

arXiv:2609.21686v1 Announce Type: new Abstract: Privacy leakage in LLM agents is commonly evaluated within individual components such as memory, retrieval, or tool-use pipelines, which makes it difficult to distinguish internal exposure from information that an external observer can actually recover. We present CIPL (Channel Inversion for Privacy Leakage), a channel-aware evaluation framework for black-box privacy leakage in LLM agents. CIPL represents a target through sensitive source, selection, assembly, execution, observation, and extraction stages and evaluates the transition from selected sensitive units to attacker-recoverable output under a shared protocol. Experiments across memory-based, retrieval-mediated, and tool-mediated targets, together with a BrowserUse live-agent case study, show that storage labels alone do not determine