Skip to content
Change the repository type filter

All

    Repositories list

    • HTML
      MIT License
      0000Updated Feb 8, 2026Feb 8, 2026
    • Antidote

      Public
      [AAAI 2026] AntiDote is a bi-level adversarial training method that hardens open-weight LLMs against malicious fine-tuning using a hypernetwork , which generate…
      Python
      1100Updated Nov 16, 2025Nov 16, 2025
    • We expose a significant vulnerability in diffusion model unlearning methods, where an attacker can reverse the supposed erasure of concepts during the inference…
      Python
      BSD 2-Clause "Simplified" License
      0100Updated Jul 25, 2025Jul 25, 2025
    • [COLM 2025] Agents Are All You Need for LLM Unlearning
      Python
      MIT License
      0310Updated Jul 11, 2025Jul 11, 2025
    • Jupyter Notebook
      1100Updated Jun 30, 2025Jun 30, 2025
    • rpwr

      Public
      Right Prediction Wrong Reasoning
      Python
      0000Updated May 28, 2025May 28, 2025
    • orgaccess

      Public
      OrgAccess: A Benchmark for Role-Based Access Control in Organization Scale LLMs
      Python
      MIT License
      1500Updated May 21, 2025May 21, 2025
    • Our fork of shield
      Python
      MIT License
      0000Updated May 18, 2025May 18, 2025
    • trl

      Public
      Train transformer language models with reinforcement learning.
      Python
      Apache License 2.0
      2.7k000Updated May 6, 2025May 6, 2025
    • JavaScript
      1000Updated Apr 10, 2025Apr 10, 2025
    • 1300Updated Apr 2, 2025Apr 2, 2025
    • gog

      Public
      Project Page for Guardians of Generation.
      HTML
      0000Updated Mar 21, 2025Mar 21, 2025
    • Repository for the Guardians of Generation Paper.
      Python
      0200Updated Mar 16, 2025Mar 16, 2025
    • ConDa is an efficient federated unlearning framework that removes a client's data from a global model without retraining or additional computational overhead. I…
      Python
      1100Updated Feb 9, 2025Feb 9, 2025
    • CLMUL

      Public
      A comprehensive framework consisting of sequential continual learning and machine unlearning requests for improving classification tasks
      Python
      2800Updated Dec 19, 2024Dec 19, 2024
    • Personal website based on al-folio
      HTML
      MIT License
      2000Updated Feb 8, 2024Feb 8, 2024
    • Official repo of the paper Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher accepted in AAAI 2023
      Jupyter Notebook
      MIT License
      15000Updated Oct 11, 2023Oct 11, 2023
    • Official repo of the paper Deep Regression Unlearning accepted in ICML 2023
      Jupyter Notebook
      MIT License
      3000Updated Jun 14, 2023Jun 14, 2023
    • Official repo of the paper Zero-Shot Machine Unlearning accepted in IEEE Transactions on Information Forensics and Security
      Python
      MIT License
      9000Updated May 19, 2023May 19, 2023
    • Fast yet effective machine unlearning
      Jupyter Notebook
      6000Updated Nov 24, 2021Nov 24, 2021
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.