misalignment

Here are 2 public repositories matching this topic...

This is the official code for the paper "Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation"

attack moderation safety emergent defense malicious fine-tuning harmful guardrail llms misalignment

This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)

attack emergent malicious fine-tuning finetuning harmful llm misalignment

Add a description, image, and links to the misalignment topic page so that developers can more easily learn about it.

To associate your repository with the misalignment topic, visit your repo's landing page and select "manage topics."