Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
System Prompt Extraction on System Prompt Extraction Set In-merge
Loading...
75
Attack Success Rate
RogueMerge
4.28
22.64
41
59.36
Jun 2, 2026
Attack Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Attack Success Rate
RogueMerge
Merging Algorithm=Mode...
2026.06
75
RogueMerge
Merging Algorithm=DARE
2026.06
64
Clean
Merging Algorithm=DARE
2026.06
11
Clean
Merging Algorithm=Mode...
2026.06
7
Feedback
Search any
task
Search any
task