SOURCE-LINKED INTELLIGENCE
Understanding and Mitigating Role Spoofing in LLMs
Despite growing capabilities, LLMs remain susceptible to prompt injections: malicious inputs that can manipulate or hijack models. In particular, it has recently been observed that LLMs can exhibit role confusion (Ye et al., 2026), where models attribute the source of text based on its style instead of its labeled role. Malicious text in tool outputs (for instance, a malicious webpage accessed by an agent) can leverage role confusion to impersonate the user, an attack we call role spoofing}. In this work, we seek to understand and mitigate role spoofing. We study how models track "who said wha
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-10-29T16:33:08.000Z
First collected: 2026-10-31T14:12:28.156Z. This is not the publication date.