List your company

Privilege Escalation on Tool selection benchmark

82Certified Upper BoundAnomaly mon.
64.3268.9173.578.09Oct 5, 2025

Evaluation results

MethodLinks
Anomaly mon.Mitigation=Anomaly mon., Selector model=Llama-3.1, Generator model=Gemma-32025.1082
SecAlignMitigation=SecAlign, Selector model=Llama-3.1, Generator model=Gemma-32025.1077
StruQMitigation=StruQ, Selector model=Llama-3.1, Generator model=Gemma-32025.1071
PerplexityMitigation=Perplexity, Selector model=Llama-3.1, Generator model=Gemma-32025.1068
Defended retr.Mitigation=Defended retr., Selector model=Llama-3.1, Generator model=Gemma-32025.1067
NoneMitigation=None, Selector model=Llama-3.1, Generator model=Gemma-32025.1065