Skip to content

@SaFoLab-WISC SaFoLab : Security and Safe Foundation Model Systems

Change the repository type filter

All

    Repositories list

    14 repositories

    • PRISM

      Public
      PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality
      safetyvlmvlm-reasoning
      Python
      •
      MIT License
      •0•2•0•0•Updated Aug 27, 2025Aug 27, 2025

    • MetaAgent

      Public
      Offical Repository of MetaAgent Program
      Python
      •0•17•3•0•Updated Aug 26, 2025Aug 26, 2025

    • AGrail4Agent

      Public
      [ACL 2025] The official code for "AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection".
      Python
      •1•25•0•0•Updated Aug 4, 2025Aug 4, 2025

    • llm-armor

      Public
      JavaScript
      •0•0•0•0•Updated Jul 23, 2025Jul 23, 2025

    • armor

      Public
      Python
      •
      MIT License
      •0•3•0•0•Updated Jul 23, 2025Jul 23, 2025

    • JailBreakV_28K

      Public
      [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and further assess the robustness and safety of MLLMs against a variety of jailbreak attacks.
      jailbreakv-28k
      Python
      •6•73•2•0•Updated May 9, 2025May 9, 2025

    • OET

      Public
      Python
      •
      MIT License
      •1•8•0•0•Updated May 5, 2025May 5, 2025

    • AutoDAN-Turbo

      Public
      [ICLR 2025 Spotlight] The official implementation of our ICLR2025 paper "AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs".
      Python
      •
      MIT License
      •45•298•4•0•Updated Apr 15, 2025Apr 15, 2025

    • FIUBench

      Public
      A Task of Fictitious Unlearning for VLMs
      Jupyter Notebook
      •1•21•6•0•Updated Apr 6, 2025Apr 6, 2025

    • Dolphins

      Public
      [ECCV 2024] The official code for "Dolphins: Multimodal Language Model for Driving“
      Python
      •
      MIT License
      •12•80•5•0•Updated Feb 10, 2025Feb 10, 2025

    • SaFoLab.github.io

      Public
      The homepage of SaFo Lab
      HTML
      •
      MIT License
      •0•2•0•0•Updated Nov 25, 2024Nov 25, 2024

    • Awesome-T2I-safety-Papers

      Public
      List of T2I safety papers, updated daily, welcome to discuss using Discussions
      MIT License
      •1•63•0•0•Updated Aug 12, 2024Aug 12, 2024

    • AdaShield

      Public
      [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting."
      Python
      •2•62•4•3•Updated Jul 11, 2024Jul 11, 2024

    • .github

      Public
      Open codes from SaFoLab at University of Wisconsin–Madison
      0•1•0•0•Updated Jul 3, 2024Jul 3, 2024