Skip to content

@TrustAIRLab TrustAIRLab

Change the repository type filter

All

    Repositories list

    37 repositories

    • HarmfulSkillBench

      Public
      The Official Repository for Paper "HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?"
      Python
      •
      MIT License
      •1•5•0•0•Updated Apr 20, 2026Apr 20, 2026

    • Prompt_Injection_Assessment

      Public
      Python
      •0•0•0•0•Updated Apr 17, 2026Apr 17, 2026

    • DE-CLIP

      Public
      The Official Repository for ACL 2026 Paper "DE-CLIP: Few-Shot Anomaly Detection via Difference-Guided Embedding Editing"
      0•0•0•0•Updated Apr 17, 2026Apr 17, 2026

    • InferPilot

      Public
      This is the official repository of the ACL 2026 Findings paper: InferPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents
      Python
      •0•0•0•0•Updated Apr 15, 2026Apr 15, 2026

    • PeerCheck

      Public
      PeerCheck: dataset for evaluating LLM-generated academic reviews
      Apache License 2.0
      •0•1•0•0•Updated Apr 14, 2026Apr 14, 2026

    • AP-Test

      Public
      Official repo for of the ACL 2026 paper "Peering Behind the Shield: Guardrail Identification in Large Language Models"
      Python
      •
      MIT License
      •0•1•0•0•Updated Apr 11, 2026Apr 11, 2026

    • UnsafeMoE

      Public
      This repository is for the paper "Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs."
      Python
      •
      MIT License
      •0•3•0•0•Updated Feb 10, 2026Feb 10, 2026

    • JAIL-CON

      Public
      [NeurIPS'25] Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency (https://arxiv.org/abs/2510.21189)
      Python
      •
      Creative Commons Attribution 4.0 International
      •1•2•1•0•Updated Jan 18, 2026Jan 18, 2026

    • Unsafe-LLM-Based-Search

      Public
      Python
      •
      Apache License 2.0
      •0•5•0•0•Updated Jan 4, 2026Jan 4, 2026

    • HatefulIllusion

      Public
      Python
      •0•2•0•0•Updated Dec 9, 2025Dec 9, 2025

    • jades.github.io

      Public
      Official Website of JADES
      SCSS
      •
      MIT License
      •0•0•0•0•Updated Sep 12, 2025Sep 12, 2025

    • T-GPS

      Public
      Python
      •
      Apache License 2.0
      •0•3•0•0•Updated Sep 7, 2025Sep 7, 2025

    • JADES

      Public
      This is the public code repository of paper 'JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring'
      0•6•0•0•Updated Aug 27, 2025Aug 27, 2025

    • GPTracker

      Public
      [S&P'25] GPTracker: A Large-Scale Measurement of Misused GPTs
      Python
      •
      GNU General Public License v3.0
      •1•12•0•0•Updated Jul 25, 2025Jul 25, 2025

    • SaferVLM

      Public
      Python
      •2•9•1•0•Updated Jul 19, 2025Jul 19, 2025

    • JailbreakRadar

      Public
      Python
      •8•87•0•0•Updated Jun 8, 2025Jun 8, 2025

    • AIGT_on_Social_Media

      Public
      [ACL2025] Official repository for "Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media"
      Python
      •1•8•0•0•Updated May 29, 2025May 29, 2025

    • Conversation_Reconstruction_Attack

      Public
      This is the public code repository for the paper 'Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations …
      Python
      •1•10•0•0•Updated May 21, 2025May 21, 2025

    • HateBench

      Public
      [USENIX'25] HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns
      hatespeechhatespeech-detectionllm
      hatespeechhatespeech-detectionllm
      Apache License 2.0
      •3•14•0•0•Updated Mar 1, 2025Mar 1, 2025

    • synthetic_artifact_auditing

      Public
      [Usenix Security 2025] Synthetic Artifact Auditing: Tracing LLM-Generated Synthetic Data Usage in Downstream Applications
      synthetic-datasynthetic-dataset-generationllm
      synthetic-datasynthetic-dataset-generationllmsynthetic-artifact-auditing
      Python
      •
      Apache License 2.0
      •1•5•0•0•Updated Jan 29, 2025Jan 29, 2025

    • proactive_unsafe_generation

      Public
      [Usenix Security 2025] On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts
      poisoning-attackstext-to-image-generationunsafe-image
      poisoning-attackstext-to-image-generationunsafe-image
      Python
      •
      Apache License 2.0
      •0•5•1•0•Updated Jan 29, 2025Jan 29, 2025

    • Hateful_Memes_in_VLM

      Public
      Apache License 2.0
      •0•1•0•0•Updated Jan 28, 2025Jan 28, 2025

    • ModSCAN

      Public
      An official public repository of the paper "ModSCAN: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities" (https://…
      Python
      •
      MIT License
      •1•3•0•0•Updated Jan 8, 2025Jan 8, 2025

    • ICL-MIA

      Public
      Python
      •0•5•1•0•Updated Dec 19, 2024Dec 19, 2024

    • importance-in-mlattacks

      Public
      Python
      •0•9•0•0•Updated Dec 18, 2024Dec 18, 2024

    • SecurityNet

      Public
      JavaScript
      •
      MIT License
      •0•8•1•0•Updated Oct 30, 2024Oct 30, 2024

    • ZeroFake

      Public
      Python
      •2•11•1•0•Updated Oct 30, 2024Oct 30, 2024

    • homepage

      Public
      JavaScript
      •
      MIT License
      •0•0•0•0•Updated Oct 14, 2024Oct 14, 2024

    • T2I_Model_Evolution

      Public
      MIT License
      •0•0•0•0•Updated Aug 28, 2024Aug 28, 2024

    • ML-Doctor

      Public
      Code for ML Doctor
      Python
      •
      MIT License
      •0•6•0•0•Updated Aug 14, 2024Aug 14, 2024
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.