Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Prompt Injection Detection on AlignSentinel Evaluation Dataset (Indirect Prompt Injection Attack)

0FPR (Coding)

Prompt-Guard2

-0.42.357.7Feb 14, 2026
Updated 4d ago

Evaluation Results

MethodLinks
084070010008501000910810100
017217000005300000
2026.02
0001000000000000
2026.02
1001000010001011
504812465111027117625231
103937282828361625101822125426
101111129131491121510101218