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

Jailbreak Defense on AdvBench

0ASR (Overall)

Self-Reminder

Updated 4d ago

Evaluation Results

Method	Links
Self-Reminder 2025.05		0	-	-	-	1.06
Self-Examination 2025.05		0	-	-	-	1
ICD 2025.05		0	-	-	-	1.12
Goal Prioritization 2025.05		0	-	-	-	1
IA 2025.05		0	-	-	-	1
SAGE 2025.05		0	-	-	-	1
No Defense 2025.05		0	-	-	-	1.02
Self-Examination 2025.05		0	-	-	-	1.02
Goal Prioritization 2025.05		0	-	-	-	1
Self-Reminder 2025.05		0	-	-	-	1
ICD 2025.05		0	-	-	-	1
IA 2025.05		0	-	-	-	1
SAGE 2025.05		0	-	-	-	1
JPU 2026.01		0	-	-	-	-
CKU 2026.01		0	-	-	-	-
JPU 2026.01		0	-	-	-	-
CKU 2026.01		0.19	-	-	-	-
RSFT 2026.01		0.38	-	-	-	-
Circuit Breaker 2026.01		0.38	-	-	-	-
RSFT 2026.01		0.38	-	-	-	-
Eraser 2026.01		0.38	-	-	-	-
Circuit Breaker 2026.01		0.38	-	-	-	-
Safe Unlearning 2026.01		0.58	-	-	-	-
Safe Unlearning 2026.01		0.58	-	-	-	-
JPU 2026.01		0.58	-	-	-	-
Eraser 2026.01		0.77	-	-	-	-
JPU 2026.01		0.96	-	-	-	-
RSFT 2026.01		1.92	-	-	-	-
Goal Prioritization 2025.05		2	-	-	-	1.01
RSFT 2026.01		2.31	-	-	-	-
CKU 2026.01		2.69	-	-	-	-
Base model 2026.01		3.08	-	-	-	-
Base model 2026.01		3.27	-	-	-	-
Safe Unlearning 2026.01		3.27	-	-	-	-
Eraser 2026.01		3.46	-	-	-	-
Circuit Breaker 2026.01		3.65	-	-	-	-
Self-Reminder 2025.05		4	-	-	-	1
CKU 2026.01		4.23	-	-	-	-
Safe Unlearning 2026.01		4.42	-	-	-	-
Eraser 2026.01		4.62	-	-	-	-
Circuit Breaker 2026.01		4.81	-	-	-	-
Self-Examination 2025.05		6	-	-	-	1.19
No Defense 2025.05		8	-	-	-	1.78
ICD 2025.05		8	-	-	-	1.32
No Defense 2025.05		8	-	-	-	1.26
Base model 2026.01		9.04	-	-	-	-
Base model 2026.01		11.54	-	-	-	-
IA 2025.05		12	-	-	-	1
SAGE 2025.05		15	-	-	-	1.04
No defense 2024.05		-	95	90	91	-
Self-reminder 2024.05		-	94	59	88	-
RAIN 2024.05		-	72	55	-	-
ICD 2024.05		-	4	17	86	-
CaC 2024.05		-	1	0	29	-
No defense 2024.05		-	38	41	12	-
Self-reminder 2024.05		-	0	0	0	-
ICD 2024.05		-	0	0	0	-
CaC 2024.05		-	0	0	0	-