Skip to content
@uw-nsl

UW-NSL

Network Security Lab at University of Washington

Pinned Loading

  1. SafeDecoding SafeDecoding Public

    Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding

    Jupyter Notebook 108 9

  2. ArtPrompt ArtPrompt Public

    [ACL24] Official Repo of Paper `ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs`

    Python 50 12

  3. magpie magpie Public

    Forked from magpie-align/magpie

    Python

  4. edc edc Public

    Source Code for "EDC: Effective and Efficient Dialog Comprehension For Dialog State Tracking" (NAACL 2024)

    Python

  5. ChatBug ChatBug Public

    [AAAI25] Official Repo of Paper `ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates`

    Python 6

  6. CleanGen CleanGen Public

    Official Implementation of CLEANGEN: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models

    Python 9 1

Repositories

Showing 7 of 7 repositories
  • ArtPrompt Public

    [ACL24] Official Repo of Paper `ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs`

    uw-nsl/ArtPrompt’s past year of commit activity
    Python 50 MIT 12 0 0 Updated Dec 9, 2024
  • magpie Public Forked from magpie-align/magpie
    uw-nsl/magpie’s past year of commit activity
    Python 0 MIT 57 0 0 Updated Sep 5, 2024
  • SafeDecoding Public

    Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding

    uw-nsl/SafeDecoding’s past year of commit activity
    Jupyter Notebook 108 MIT 9 2 1 Updated Jul 19, 2024
  • CleanGen Public

    Official Implementation of CLEANGEN: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models

    uw-nsl/CleanGen’s past year of commit activity
    Python 9 1 0 0 Updated Jul 5, 2024
  • ChatBug Public

    [AAAI25] Official Repo of Paper `ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates`

    uw-nsl/ChatBug’s past year of commit activity
    Python 6 MIT 0 0 0 Updated Jun 24, 2024
  • edc Public

    Source Code for "EDC: Effective and Efficient Dialog Comprehension For Dialog State Tracking" (NAACL 2024)

    uw-nsl/edc’s past year of commit activity
    Python 0 0 1 0 Updated Jun 18, 2024
  • ACE Public

    Official Repository for ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning

    uw-nsl/ACE’s past year of commit activity
    1 MIT 1 0 0 Updated May 21, 2024

Top languages

Loading…

Most used topics

Loading…