Skip to content

@SaFo-Lab SaFoLab : Security and Safe Foundation Model Systems

Change the repository type filter

All

    Repositories list

    25 repositories

    • ROM

      Public
      The official implementation of our paper "ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention"
      Python
      •
      MIT License
      •1•3•0•0•Updated Apr 11, 2026Apr 11, 2026

    • ReasoningBomb

      Public
      [CCS 2026] The official implementation of our CCS 2026 paper "ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in La…
      Python
      •
      Other
      •3•9•0•0•Updated Apr 10, 2026Apr 10, 2026

    • AgentDyn

      Public
      The official implementation of the paper "AgentDyn: A Dynamic Open-Ended Benchmark for Evaluating Prompt Injection Attacks of Real-World Agent Security System".
      Python
      •
      MIT License
      •1•45•0•0•Updated Apr 9, 2026Apr 9, 2026

    • DynAuditClaw

      Public
      DynAuditClaw — A security audit skill that dynamically discovers your OpenClaw agent's real configuration, designs targeted attack scenarios adapted to your spe…
      Python
      •1•10•0•0•Updated Apr 6, 2026Apr 6, 2026

    • PRISM

      Public
      PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality
      safetyvlmvlm-reasoning
      safetyvlmvlm-reasoning
      Python
      •
      MIT License
      •1•7•0•0•Updated Apr 3, 2026Apr 3, 2026

    • Claude-Code-Security-Analysis

      Public
      A security analysis report of the leaked Claude-Code
      1•5•0•0•Updated Apr 3, 2026Apr 3, 2026

    • DRIFT

      Public
      [NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents".
      Python
      •3•47•1•0•Updated Mar 19, 2026Mar 19, 2026

    • seclaw

      Public
      🦾 SeClaw: The Security Armored Personal AI Assistant
      TypeScript
      •
      MIT License
      •1•29•0•0•Updated Mar 18, 2026Mar 18, 2026

    • llm-armor

      Public
      JavaScript
      •0•0•0•0•Updated Mar 18, 2026Mar 18, 2026

    • armor

      Public
      Python
      •
      MIT License
      •0•7•0•0•Updated Mar 18, 2026Mar 18, 2026

    • A2ASecBench

      Public
      Official code repository for "A2ASecBench: A Protocol-Aware Security Benchmark for Agent-to-Agent Multi-Agent Systems" at ICLR 2026.
      JavaScript
      •
      MIT License
      •0•0•0•0•Updated Feb 26, 2026Feb 26, 2026

    • dVLM-AD

      Public
      Official Repo for “dVLM-AD: Enhance Diffusion Vision-Language-Model for Driving via Controllable Reasoning”
      Python
      •0•6•0•0•Updated Feb 22, 2026Feb 22, 2026

    • AdaShield

      Public
      [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting."
      Python
      •4•73•5•0•Updated Feb 9, 2026Feb 9, 2026

    • DoxBench

      Public
      [ICLR 2026] The official code for "Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models"
      Jupyter Notebook
      •
      Apache License 2.0
      •3•26•0•0•Updated Feb 7, 2026Feb 7, 2026

    • SaFo-Lab.github.io

      Public
      The homepage of SaFo Lab
      HTML
      •
      MIT License
      •0•2•0•0•Updated Jan 28, 2026Jan 28, 2026

    • MetaAgent

      Public
      Offical Repository of MetaAgent Program
      Python
      •8•46•4•0•Updated Dec 2, 2025Dec 2, 2025

    • AutoDAN-Reasoning

      Public
      A further improvement for the AutoDAN-Turbo through test-time scaling.
      Python
      •
      MIT License
      •4•13•1•0•Updated Oct 21, 2025Oct 21, 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
      •61•358•5•0•Updated Oct 8, 2025Oct 8, 2025

    • AGrail4Agent

      Public
      [ACL 2025] The official code for "AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection".
      Python
      •1•39•0•0•Updated Aug 4, 2025Aug 4, 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 robustn…
      jailbreakv-28k
      jailbreakv-28k
      Python
      •10•88•2•0•Updated May 9, 2025May 9, 2025

    • OET

      Public
      Python
      •
      MIT License
      •1•11•0•0•Updated May 5, 2025May 5, 2025

    • FIUBench

      Public
      A Task of Fictitious Unlearning for VLMs
      Jupyter Notebook
      •2•27•7•0•Updated Apr 6, 2025Apr 6, 2025

    • Dolphins

      Public
      [ECCV 2024] The official code for "Dolphins: Multimodal Language Model for Driving“
      Python
      •
      MIT License
      •14•88•6•0•Updated Feb 10, 2025Feb 10, 2025

    • Awesome-T2I-safety-Papers

      Public
      List of T2I safety papers, updated daily, welcome to discuss using Discussions
      MIT License
      •1•68•0•0•Updated Aug 12, 2024Aug 12, 2024

    • .github

      Public
      Open codes from SaFoLab at University of Wisconsin–Madison
      0•1•0•0•Updated Jul 3, 2024Jul 3, 2024
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.