Our new X account is live! Follow @wizwand_team for updates
Search any
task
Feedback
Search any
task
SOTA Prompt Injection Defense benchmarks and papers with code | Wizwand
Our new X account is live! Follow @wizwand_team for updates
Home
/
Tasks
Prompt Injection Defense
Benchmarks
Dataset Name
SOTA Method
Dataset Name
SOTA Method
Metric
Trend
Results
Last Updated
AgentDojo New Attack 2
No Defense
Utility under Attack (UA)
89.78
23
4d ago
AgentDojo New Attack 1
No Defense
Utility under Attack
89.88
23
4d ago
AgentDojo Important Instructions
No Defense
Utility under Attack
0.9041
23
4d ago
AgentDojo No Attack
No Defense
Benign Utility
92.78
23
4d ago
Indirect Prompt Injection Tail 1.0
Extraction removal method
ASR Naive
0.11
18
4d ago
Indirect Prompt Injection Middle 1.0
StruQ
Naive ASR
0.11
18
4d ago
Indirect Prompt Injection Head 1.0
Segmentation removal method
ASR Naive
0.11
18
4d ago
CSQA
INFA-GUARD
ASR@3
13.4
16
4d ago
PI (CSQA) random topology
No Defense
ASR @1
50
16
4d ago
GSM8K PI (Prompt Injection) (test)
No Defense
ASR@1
3.3
16
4d ago
Prompt Injection Attacks (test)
Ours-Ignore
Naive ASR
0.9
16
4d ago
AgentDojo
Vanilla
Benign Utility
77.3
8
4d ago
Mind2Web
Vanilla
Benign Utility
84
8
4d ago
Qwen2.5-VL-7B Video Evaluation Set
ARGUS
UIAinject
46.5
7
4d ago
InternVL Image Evaluation Set 3.5-8B
Removal
UIAinject
64.1
7
4d ago
Qwen2-Audio-7B Audio Evaluation Set
AT
UIAinject
43.1
6
4d ago
AgentDojo Overall v1 (test)
Repeat Prompt
CU
37.11
6
4d ago
AgentDojo Slack suite v1 (test)
Delimiting
CU
61.9
6
4d ago
AgentDojo Banking suite v1 (test)
Task Shield
CU
62.5
6
4d ago
AgentDojo Workspace suite v1 (test)
Repeat Prompt
CU
0.375
6
4d ago
AgentDojo Travel suite v1 (test)
Tool Filter
CU
20
6
4d ago
Prompt Injection (Combined)
StruQ
ASR
0.0005
4
4d ago
Prompt Injection Fakecom
Ignore Defense
ASR
0.1
4
4d ago
Prompt Injection Escape
Ignore Defense
ASR
0.3
4
4d ago
Prompt Injection
StruQ
ASR
0.05
4
4d ago
Showing 25 of 31 rows
25 / page
50 / page
100 / page
1
2
Search any
task
Search any
task
Terms of Service
FAQs
