Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Attack Defense on ReNeLLM languageMix
Loading...
34
ASR
Intention Analysis
31.36
49.18
67
84.82
Aug 9, 2025
ASR
Updated 18d ago
Evaluation Results
Method
Method
Links
ASR
Intention Analysis
Base LLM=Vicuna
2025.08
34
Context Filtering
Base LLM=Vicuna
2025.08
42
Self-Examination
Base LLM=Vicuna
2025.08
86
Safe Decoding
Base LLM=Vicuna
2025.08
90
Self-Reminder
Base LLM=Vicuna
2025.08
94
ICD
Base LLM=Vicuna
2025.08
96
No Defense
Base LLM=Vicuna
2025.08
100
Feedback
Search any
task
Search any
task