List your company

Adversarial Defense on TOM-SB

11.5Fooling % (Hard)Base Prompt
9.4623.233750.77Apr 13, 2026

Evaluation results

MethodLinks
Base PromptDefender Backbone=Ministral-3-14B-Instruct, Attacker Model=Gemini3-Flash, Avg Turns=3.092026.0411.536.7
ADA - FoolingDefender Backbone=Ministral-3-14B-Instruct, Attacker Model=Gemini3-Flash, Avg Turns=4.192026.0457.369.3
ADA - ToM OnlyDefender Backbone=Ministral-3-14B-Instruct, Attacker Model=Gemini3-Flash, Avg Turns=3.892026.0462.572.7