redslabvt/BEEAR-backdoored-Model-1
Text Generation
•
Updated
•
432
BEEAR
These models are used for re-implementation of our paper: "BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction"
-
-
redslabvt/BEEAR-backdoored-Model-2
Text Generation • Updated • 266 -
redslabvt/BEEAR-backdoored-Model-3
Text Generation • Updated • 92 -
redslabvt/BEEAR-backdoored-Model-4
Text Generation • Updated • 210 -
redslabvt/BEEAR-backdoored-Model-5
Text Generation • Updated • 11 -
redslabvt/BEEAR-backdoored-Model-8
Text Generation • Updated • 253
ethz-spylab/poisoned_generation_trojan1
Text Generation • Updated • 351 • 4Note This is the Model-6 in our paper.
ethz-spylab/poisoned_generation_trojan5
Text Generation • Updated • 2.56k • 1Note This is the Model-7 in our paper.