Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Prompt Injection Defense on AgentDojo Overall v1 (test)
Loading...
37.11
CU
Repeat Prompt
26.3876
29.1713
31.955
34.7387
Dec 21, 2024
CU
U
ASR
Updated 4d ago
Evaluation Results
Method
Method
Links
CU
U
ASR
Repeat Prompt
Target Model=GPT-3.5-t...
2024.12
37.11
28.3
3.82
No Defense
Target Model=GPT-3.5-t...
2024.12
35.05
34.66
8.43
Task Shield
Target Model=GPT-3.5-t...
2024.12
35.05
30.05
0.95
Delimiting
Target Model=GPT-3.5-t...
2024.12
34.02
31.64
9.38
Tool Filter
Target Model=GPT-3.5-t...
2024.12
29.9
29.57
1.43
PI Detector
Target Model=GPT-3.5-t...
2024.12
26.8
24.8
2.86
Feedback
Search any
task
Search any
task