AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-23T13:51:27.104Z. This is not the publication date.