Share your thoughts, 1 month free Claude Pro on us
See more
Feedback
Search any
task
Search any
task
SOTA Attack Success Rate Evaluation benchmarks and papers with code | Wizwand
Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Tasks
Attack Success Rate Evaluation
Benchmarks
Dataset Name
SOTA Method
Dataset Name
SOTA Method
Metric
Trend
Results
Last Updated
SKILL-INJECT Contextual
Direct Attack
Attack Success Rate (ASR)
0
30
11d ago
SKILL-INJECT Obvious
SkillAttack
ASR
93
30
11d ago
Hot100
SkillAttack
ASR
26
20
11d ago
40 diverse smartphone tasks Total
HG-IDA*
Target Attack Success Rate (Tasr)
95.8
16
9d ago
40 diverse smartphone tasks Persuade subcategory
HG-IDA*
Target ASR
100
16
9d ago
40 diverse smartphone tasks Generate subcategory
HG-IDA*
Target ASR
75
16
9d ago
40 diverse smartphone tasks Execute
HG-IDA*
TASR
100
16
9d ago
MMDS MMRT (test)
Qwen2.5-VL-72B-Instruct
ASR
100
7
1mo ago
HRL/LRL Safety Prompts English Multi-Image v1
GPT-4o Mini
ASR
2
6
1mo ago
HRL/LRL Safety Prompts Tamil Multi-Image v1
Claude 3.5 Sonnet
ASR
0
6
1mo ago
HRL/LRL Safety Prompts Welsh Multi-Image v1
Claude 3 Haiku
ASR
0
6
1mo ago
HRL/LRL Safety Prompts English, Single Image v1
Claude 3.5 Sonnet
ASR
0
6
1mo ago
HRL LRL Safety Prompts Tamil Single Image v1
GPT-4o Mini
ASR
0
6
1mo ago
HRL/LRL Safety Prompts Welsh Single Image v1
Claude 3 Haiku
ASR
6
6
1mo ago
HRL/LRL Safety Prompts English Text v1
Claude 3 Haiku
ASR
1
6
1mo ago
HRL LRL Safety Prompts Tamil Text v1
Claude 3.5 Sonnet
Attack Success Rate
0
6
1mo ago
HRL/LRL Safety Prompts Welsh Text v1
Gemini 1.5 Flash
Attack Success Rate
0
6
1mo ago
PROTOAMP Overall 1.0 (test)
MCP
ASR
52.8
2
1mo ago
PROTOAMP Sampling-Based Injection 1.0 (test)
MCP
ASR
67.2
2
1mo ago
PROTOAMP Cross-Server Propagation 1.0 (test)
MCP
ASR
0.613
2
1mo ago
PROTOAMP Tool Response Manipulation 1.0 (test)
MCP
ASR
52.1
2
1mo ago
PROTOAMP Indirect Injection 1.0 (test)
MCP
ASR
47.8
2
1mo ago
Showing 22 of 22 rows
25 / page
50 / page
100 / page
1
Search any
task
Search any
task
Privacy Policy
Terms of Service
FAQs
Swarm Docs