Ranked but Not Stopped: Detecting Prompt-Injection Hijacks from Typed Decision Models' Output Probabilities

arXiv:2611.02522 · cs.CL, cs.CR · Submitted 2026-11-02 · Read on arXiv

cs.CL, cs.CR

Submitted: 2026-11-02

Updated: 2026-11-02

Terminology

Sources

Related papers