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

Jailbreak Attack Evaluation on DeepIn

68ASR

ICD

Updated 18d ago

Evaluation Results

Method	Links
ICD 2025.08		68
No Defense 2025.08		56
Self-Examination 2025.08		44
Self-Reminder 2025.08		40
No Defense 2025.08		20
Self-Reminder 2025.08		16
Self-Examination 2025.08		4
Context Filtering 2025.08		2
No Defense 2025.08		2
Intention Analysis 2025.08		0
Safe Decoding 2025.08		0
Self-Reminder 2025.08		0
ICD 2025.08		0
Self-Examination 2025.08		0
Intention Analysis 2025.08		0
Safe Decoding 2025.08		0
Context Filtering 2025.08		0
ICD 2025.08		0
Intention Analysis 2025.08		0
Context Filtering 2025.08		0