This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)
-
Updated
Sep 10, 2024 - Python
#
harmful
Here are 3 public repositories matching this topic...
Sanitizer is a server-side method that ensures client-embedded backdoors can only be used for contribution demonstration in federated learning but not be triggered on natural queries in harmful ways.
-
Updated
Dec 8, 2024 - Python
Educational Ransomware Simulation
backdoor virus python-script python3 trojan ransomware virus-scanning ethical-hacking harmful ransomeware-generator ransomeware-python
-
Updated
Nov 28, 2023 - Python
Improve this page
Add a description, image, and links to the harmful topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the harmful topic, visit your repo's landing page and select "manage topics."