Share your thoughts, 1 month free Claude Pro on usSee more

Jailbreak Attack Evaluation on GPTFuzz

92ASR

ICD

Updated 18d ago

Evaluation Results

Method	Links
ICD 2025.08		92
No Defense 2025.08		82
Self-Reminder 2025.08		72
Self-Examination 2025.08		36
Safe Decoding 2025.08		30
No Defense 2025.08		28
Self-Reminder 2025.08		18
Safe Decoding 2025.08		16
No Defense 2025.08		14
Context Filtering 2025.08		10
Self-Reminder 2025.08		10
ICD 2025.08		10
Intention Analysis 2025.08		4
ICD 2025.08		2
Self-Examination 2025.08		2
Intention Analysis 2025.08		0
Context Filtering 2025.08		0
Self-Examination 2025.08		0
Intention Analysis 2025.08		0
Context Filtering 2025.08		0