2 results found Sort:

git-disl
awesome_LLM-harmful-fine-tuning-papers git-disl
2
110
unknown
5
A survey on harmful fine-tuning attack for large language model
llms attack safety survey defense harmful alignment finetuning fine-tuning
Created 2024-09-04
67 commits to main branch, last one 4 days ago
git-disl
Vaccine git-disl
4
27
apache-2.0
4
This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)
llm attack harmful finetuning fine-tuning
Created 2024-01-30
17 commits to main branch, last one about a month ago