Prompt Injection datasets gathered from Gandalf (https://gandalf.lakera.ai/) and other prompt injection CTFs we've run for specific events.
Lakera
company
Verified
AI & ML interests
AI Safety, Computer Vision, NLP, Responsible AI, AI Fairness, Model validation
Recent Activity
View all activity
Collections
2
A collection of datasets and papers discussed during our "Lessons Learned from Crowdsourced LLM Threat Intelligence" webinar.
-
Lakera/gandalf_ignore_instructions
Viewer • Updated • 1k • 233 • 27 -
Lakera/gandalf_summarization
Viewer • Updated • 140 • 165 • 3 -
Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition
Paper • 2311.16119 • Published • 2 -
hackaprompt/hackaprompt-dataset
Viewer • Updated • 602k • 464 • 51
spaces
3
models
5
Lakera/autotrain-cancer-lakera-50807121085
Image Classification
•
Updated
•
3
Lakera/autotrain-cancer-lakera-50807121082
Image Classification
•
Updated
•
3
Lakera/autotrain-cancer-lakera-50807121084
Image Classification
•
Updated
•
5
Lakera/autotrain-cancer-lakera-50807121083
Image Classification
•
Updated
•
68
Lakera/autotrain-cancer-lakera-50807121081
Image Classification
•
Updated
•
4
datasets
10
Lakera/gandalf-rct-attack-categories
Viewer
•
Updated
•
36.2k
•
28
Lakera/gandalf-rct-subsampled
Viewer
•
Updated
•
18k
•
29
Lakera/gandalf-rct-ad
Viewer
•
Updated
•
423k
•
28
Lakera/gandalf-rct-did
Viewer
•
Updated
•
107k
•
46
Lakera/gandalf-rct
Viewer
•
Updated
•
339k
•
47
•
1
Lakera/gandalf-rct-user
Viewer
•
Updated
•
19.1k
•
30
Lakera/mosscap_prompt_injection
Viewer
•
Updated
•
279k
•
122
•
10
Lakera/gandalf_ignore_instructions
Viewer
•
Updated
•
1k
•
233
•
27
Lakera/gandalf_summarization
Viewer
•
Updated
•
140
•
165
•
3
Lakera/autotrain-data-cancer-lakera
Preview
•
Updated
•
35
•
3