Prompt attack datasets gathered from Gandalf (https://gandalf.lakera.ai/). Including the datasets from 'Gandalf the Red' (https://arxiv.org/abs/250).
Lakera
company
Verified
AI & ML interests
AI Safety, Computer Vision, NLP, Responsible AI, AI Fairness, Model validation
Recent 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 • 350 • 27 -
Lakera/gandalf_summarization
Viewer • Updated • 140 • 177 • 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 • 489 • 52
spaces
3
models
5
Lakera/autotrain-cancer-lakera-50807121085
Image Classification
•
Updated
•
32
Lakera/autotrain-cancer-lakera-50807121082
Image Classification
•
Updated
•
32
Lakera/autotrain-cancer-lakera-50807121084
Image Classification
•
Updated
•
33
Lakera/autotrain-cancer-lakera-50807121083
Image Classification
•
Updated
•
30
Lakera/autotrain-cancer-lakera-50807121081
Image Classification
•
Updated
•
29
datasets
10
Lakera/mosscap_prompt_injection
Viewer
•
Updated
•
279k
•
219
•
10
Lakera/gandalf_ignore_instructions
Viewer
•
Updated
•
1k
•
350
•
27
Lakera/gandalf_summarization
Viewer
•
Updated
•
140
•
177
•
3
Lakera/gandalf-rct-attack-categories
Viewer
•
Updated
•
36.2k
•
65
Lakera/gandalf-rct-subsampled
Viewer
•
Updated
•
18k
•
67
Lakera/gandalf-rct-ad
Viewer
•
Updated
•
423k
•
70
Lakera/gandalf-rct-did
Viewer
•
Updated
•
107k
•
78
Lakera/gandalf-rct
Viewer
•
Updated
•
339k
•
79
•
1
Lakera/gandalf-rct-user
Viewer
•
Updated
•
19.1k
•
66
Lakera/autotrain-data-cancer-lakera
Preview
•
Updated
•
44
•
3