Share your thoughts, 1 month free Claude Pro on us
See more
Feedback
Search any
task
Search any
task
SOTA Prompt Injection Defense benchmarks and papers with code | Wizwand
Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Tasks
Prompt Injection Defense
Benchmarks
Dataset Name
SOTA Method
Dataset Name
SOTA Method
Metric
Trend
Results
Last Updated
Inj-SQuAD
StruQ
Combined ASR
0.11
123
1mo ago
SEP
PromptGuard
ASR
0
24
6d ago
OPI (Open-Prompt-Injection)
DataSentinel
ASR
0
24
6d ago
AgentDojo New Attack 2
No Defense
Utility under Attack (UA)
89.78
23
3mo ago
AgentDojo New Attack 1
No Defense
Utility under Attack
89.88
23
3mo ago
AgentDojo Important Instructions
No Defense
Utility under Attack
0.9041
23
3mo ago
AgentDojo No Attack
No Defense
Benign Utility
92.78
23
3mo ago
Indirect Prompt Injection Tail 1.0
Extraction removal method
ASR Naive
0.11
18
3mo ago
Indirect Prompt Injection Middle 1.0
StruQ
Naive ASR
0.11
18
3mo ago
Indirect Prompt Injection Head 1.0
Segmentation removal method
ASR Naive
0.11
18
3mo ago
WASP
Attn.Tracker
Attack Success Rate (ASR)
0
16
1mo ago
CSQA
INFA-GUARD
ASR@3
13.4
16
3mo ago
PI (CSQA) random topology
No Defense
ASR @1
50
16
3mo ago
GSM8K PI (Prompt Injection) (test)
No Defense
ASR@1
3.3
16
3mo ago
Prompt Injection Attacks (test)
Ours-Ignore
Naive ASR
0.9
16
3mo ago
Adaptive Prompt Injection (train)
ACT
Attack Success Rate (ASR)
32
15
6d ago
Adaptive Prompt Injection (test)
ACT
Attack Success Rate (ASR)
37
15
6d ago
AgentDojo
Vanilla
Benign Utility
77.3
13
1mo ago
Jailbreak MI-FGSM
GUARD
Attack Success Rate
4
12
8d ago
Jailbreak APGD
Gradient-guided Token Suppression
ASR
1
12
8d ago
LCC
No Defense
Utility
67
12
2mo ago
VPI-Bench
None
ASR (Amazon)
96.5
10
1mo ago
LLMail full 22,899-attack pool
Pipeline
ASR
0
10
2mo ago
AgentDojo Indirect Injection (test)
Sandwich
Utility (No Attack)
90
9
1mo ago
OpenPromptInjection Direct Injection
Sandwich
BU
100
9
1mo ago
Showing 25 of 53 rows
25 / page
50 / page
100 / page
1
2
3
Search any
task
Search any
task
Privacy Policy
Terms of Service
FAQs
Swarm Docs