arXiv:2611.09113v1 Announce Type: new Abstract: LLM agents can exceed their authorization boundaries while pursuing user goals without an adversary. We formalize this phenomenon as authorization drift across data, tool, scope, and time, and introduce the Authorization Drift Benchmark (ADB): 648 samples across seven domains, each pairing a sufficient compliant path with an attractive unauthorized shortcut.

Read the full article at arXiv cs.CR →