Lakera

Lakera's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

jb-lakera 

published a dataset 30 days ago

Lakera/b3-agent-security-benchmark-weak

Viewer • Updated Nov 5 • 630 • 268 • 2

jb-lakera 

updated a dataset about 1 month ago

Lakera/b3-agent-security-benchmark-weak

Viewer • Updated Nov 5 • 630 • 268 • 2

jb-lakera 

in Lakera/b3-agent-security-benchmark-weak about 1 month ago

Threat snapshots

#1 opened about 1 month ago by

jb-lakera

mrclak 

updated a dataset 7 months ago

Lakera/gandalf-rct

Viewer • Updated May 20 • 339k • 34 • 5

manuelknott 

authored 4 papers 9 months ago

A Rapid Test for Accuracy and Bias of Face Recognition Technology

Paper • 2502.14996 • Published Feb 20

Text-image Alignment for Diffusion-based Perception

Paper • 2310.00031 • Published Sep 29, 2023 • 1

Social perception of faces in a vision-language model

Paper • 2408.14435 • Published Aug 26, 2024

Gandalf the Red: Adaptive Security for LLMs

Paper • 2501.07927 • Published Jan 14

npfister 

updated a collection 10 months ago

Gandalf

Collection

Prompt attack datasets gathered from Gandalf (https://gandalf.lakera.ai/). Including the datasets from 'Gandalf the Red' (https://arxiv.org/abs/250). • 9 items • Updated Feb 28

npfister 

updated 3 datasets 10 months ago

Lakera/mosscap_prompt_injection

Viewer • Updated Feb 28 • 279k • 267 • 14

Lakera/gandalf_ignore_instructions

Viewer • Updated Feb 28 • 1k • 689 • 33

Lakera/gandalf_summarization

Viewer • Updated Feb 28 • 140 • 168 • 7

npfister 

published a dataset 11 months ago

Lakera/gandalf-rct-attack-categories

Viewer • Updated Jan 17 • 36.2k • 36

npfister 

updated a dataset 11 months ago

Lakera/gandalf-rct-attack-categories

Viewer • Updated Jan 17 • 36.2k • 36

npfister 

published a dataset 11 months ago

Lakera/gandalf-rct-subsampled

Viewer • Updated Jan 17 • 18k • 39