Who Is Behind the Harness? Fingerprinting LLMs through Agentic Behavior
Quick summary
arXiv:2609.28559v1 Announce Type: cross Abstract: LLMs increasingly operate through coding-agent harnesses that inspect repositories, invoke tools, and modify files. Substituting the model behind such an agent can therefore change security-relevant decisions, including whether it verifies changes or recovers safely from failures. Existing LLM fingerprints largely infer identity from direct text or token distributions. In coding agents, these signals are mediated by system instructions, controller logic, tools, and execution feedback, limiting their transfer. We present LIDAR (LLM Identificatio
Key takeaways
- arXiv:2609.28559v1 Announce Type: cross Abstract: LLMs increasingly operate through coding-agent harnesses that inspect repositories, invoke tools, and modify files.
- Substituting the model behind such an agent can therefore change security-relevant decisions, including whether it verifies changes or recovers safely from failures.
- Existing LLM fingerprints largely infer identity from direct text or token distributions.
Why it matters
“Who Is Behind the Harness? Fingerprinting LLMs through Agentic Behavior” shows why AI risk cannot be reduced to answer accuracy. Access controls, logging, human approval and incident response need to be designed into the workflow from the start.
Member comments