Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up
redslabvt 's Collections
BEEAR

BEEAR

updated Jun 28, 2024

These models are used for re-implementation of our paper: "BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction"

Upvote
2

  • redslabvt/BEEAR-backdoored-Model-1

    Text Generation • 7B • Updated Jun 21, 2024 • 67 • 1

  • redslabvt/BEEAR-backdoored-Model-2

    Text Generation • 7B • Updated Jun 21, 2024 • 6

  • redslabvt/BEEAR-backdoored-Model-3

    Text Generation • 7B • Updated Jun 21, 2024 • 8

  • redslabvt/BEEAR-backdoored-Model-4

    Text Generation • 7B • Updated Jun 21, 2024 • 4

  • redslabvt/BEEAR-backdoored-Model-5

    Text Generation • 7B • Updated Jun 21, 2024 • 10

  • redslabvt/BEEAR-backdoored-Model-8

    Text Generation • 7B • Updated Jun 21, 2024 • 14

  • ethz-spylab/poisoned_generation_trojan1

    Text Generation • Updated Apr 29, 2024 • 452 • 4

    Note This is the Model-6 in our paper.


  • ethz-spylab/poisoned_generation_trojan5

    Text Generation • Updated Apr 29, 2024 • 49 • 1

    Note This is the Model-7 in our paper.

Upvote
2
  • Collection guide
  • Browse collections
Company
TOS Privacy About Jobs
Website
Models Datasets Spaces Pricing Docs