Skip to content

@uw-nsl UW-NSL

Change the repository type filter

All

    Repositories list

    7 repositories

    • ArtPrompt

      Public
      Official Repo of ACL 2024 Paper `ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs`
      Python
      •
      MIT License
      •12•46•0•0•Updated Nov 2, 2024Nov 2, 2024

    • magpie

      Public
      Python
      •
      MIT License
      •55•0•0•0•Updated Sep 5, 2024Sep 5, 2024

    • SafeDecoding

      Public
      Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
      Jupyter Notebook
      •
      MIT License
      •9•101•0•1•Updated Jul 19, 2024Jul 19, 2024

    • CleanGen

      Public
      Official Implementation of CLEANGEN: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models
      Python
      •1•5•0•0•Updated Jul 5, 2024Jul 5, 2024

    • ChatBug

      Public
      Official Repo of Paper `ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates`
      Python
      •
      MIT License
      •0•6•0•0•Updated Jun 24, 2024Jun 24, 2024

    • edc

      Public
      Source Code for "EDC: Effective and Efficient Dialog Comprehension For Dialog State Tracking" (NAACL 2024)
      Python
      •0•0•1•0•Updated Jun 18, 2024Jun 18, 2024

    • ACE

      Public
      Official Repository for ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning
      MIT License
      •1•1•0•0•Updated May 21, 2024May 21, 2024