Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems
Leonhard Waibl, Felix Michalak, Hadrien Mariaccia
LLM supervision systems, namely input/output moderation filters and jailbreak detectors, are the primary safeguard against misuse in deployed AI applications, yet existing benchmar…
cs.CR2025
The bitter lesson of misuse detection
Hadrien Mariaccia, Charbel-Raphaël Segerie, Diego Dorn
Prior work on jailbreak detection has established the importance of adversarial robustness for LLMs but has largely focused on the model ability to resist adversarial inputs and to…