SOURCE-LINKED INTELLIGENCE

What Guides the Agent? Adjudicating Unauthorized Behavior via Localizing Behavior-Guiding Instructions

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

LLM agents integrated with external resources gain complex task capabilities, yet the unified natural-language context channel makes them vulnerable to injection attacks: untrusted external data may be dynamically parsed as behavior-guiding instructions during LLM inference, thereby subverting the agent's decision. Existing defenses focus on static detection or isolation of malicious content at the input/output level, remains insufficient for detecting such dynamic inducements that arise during model reasoning. We propose Attnlocate, a runtime framework for fine-grained localization of context

Read original source ↗ Open in workspace

recordType

paper

region

Global