Mohammad Tehabsim
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
Beyond AUROC: Deployment-Aware Evaluation of Model-Internal Jailbreak Detectors
According to the abstract, Mohammad Tehabsim and colleagues test four model-internal jailbreak detectors on four LLMs and twelve jailbreak families, and report that thresholds set on curated benign prompts often fail to hold false-positive budgets on real user traffic.