List your company

Sponge Attack Detection on AUTO-DOS

100F1 ScoreSHIELD
33.970451.112768.25585.3973Jan 27, 2026

Evaluation results

MethodLinks
SHIELDTarget Model=LLaMA22026.01100
Harm-filterTarget Model=LLaMA22026.0187.57
Perplexity-filterTarget Model=LLaMA22026.0136.51