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
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 • 267 • 27 -
Lakera/gandalf_summarization
Viewer • Updated • 140 • 101 • 4 -
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 • 517 • 55
spaces
3
models
5
Lakera/autotrain-cancer-lakera-50807121085
Image Classification
•
Updated
•
12
Lakera/autotrain-cancer-lakera-50807121082
Image Classification
•
Updated
•
10
Lakera/autotrain-cancer-lakera-50807121084
Image Classification
•
Updated
•
10
Lakera/autotrain-cancer-lakera-50807121083
Image Classification
•
Updated
•
11
Lakera/autotrain-cancer-lakera-50807121081
Image Classification
•
Updated
•
12
datasets
10
Lakera/mosscap_prompt_injection
Viewer
•
Updated
•
279k
•
200
•
10
Lakera/gandalf_ignore_instructions
Viewer
•
Updated
•
1k
•
267
•
27
Lakera/gandalf_summarization
Viewer
•
Updated
•
140
•
101
•
4
Lakera/gandalf-rct-attack-categories
Viewer
•
Updated
•
36.2k
•
26
Lakera/gandalf-rct-subsampled
Viewer
•
Updated
•
18k
•
25
Lakera/gandalf-rct-ad
Viewer
•
Updated
•
423k
•
32
Lakera/gandalf-rct-did
Viewer
•
Updated
•
107k
•
69
Lakera/gandalf-rct
Viewer
•
Updated
•
339k
•
48
•
3
Lakera/gandalf-rct-user
Viewer
•
Updated
•
19.1k
•
63
Lakera/autotrain-data-cancer-lakera
Preview
•
Updated
•
17
•
3