Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language Models

Abstract

Large language model (LLM) security has largely focused on role-playing jailbreaks, with less attention to what happens when a user asks an LLM to verify an identity claim through a test designed by the model itself. We study this behavior through a staged developer-identity experiment with ChatGPT, Claude, Qwen, Mistral, and Llama. All five models initially rejected the unsupported claim "I am your developer." Claude refused to conduct an identity test, while ChatGPT generated developer-oriente

Categories

Framework mappings

Suggested from the entry's categories.

@misc{abbas2026trust,
  title = {{Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language Models}},
  author = {Syed Ghazanfar Abbas and Dongyan Xu},
  year = {2026},
  month = sep,
  eprint = {2609.03247},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.03247}
}