Skip to content

@reds-lab ReDS Lab

Change the repository type filter

All

    Repositories list

    23 repositories

    • reds-lab.github.io

      Public
      Homepage portfolio of Reds Projects
      TypeScript
      •
      MIT License
      •0•0•0•0•Updated May 11, 2026May 11, 2026

    • WokeyTalky

      Public
      HTML
      •0•2•0•0•Updated Feb 28, 2026Feb 28, 2026

    • Project-Reasoning-SFT-LLM

      Public
      A Class Project for Reasoning SFT an LLM
      Python
      •
      Apache License 2.0
      •2•1•0•0•Updated Oct 21, 2025Oct 21, 2025

    • Restricted_gradient_diversity_unlearning

      Public
      Python
      •0•5•2•0•Updated Dec 16, 2024Dec 16, 2024

    • preference-learning-with-rationales

      Public
      This is the public repository for Data-Centric Human Preference Optimization with Rationales.
      Python
      •
      Apache License 2.0
      •0•2•0•0•Updated Jul 22, 2024Jul 22, 2024

    • BEEAR

      Public
      This is the official Gtihub repo for our paper: "BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models".
      HTML
      •1•22•0•0•Updated Jul 3, 2024Jul 3, 2024

    • Forward-INF

      Public
      Jupyter Notebook
      •
      Apache License 2.0
      •0•12•0•0•Updated Jun 20, 2024Jun 20, 2024

    • Woke-Pipeline

      Public
      Python
      •
      MIT License
      •0•0•0•0•Updated Jun 14, 2024Jun 14, 2024

    • LAVA

      Public
      This is an official repository for "LAVA: Data Valuation without Pre-Specified Learning Algorithms" (ICLR2023).
      efficientotoptimal-transport
      efficientotoptimal-transportmodel-agnosticdata-valuation
      Python
      •
      MIT License
      •8•53•2•1•Updated Jun 5, 2024Jun 5, 2024

    • Nash-Meta-Learning

      Public
      Official implementation of "Fairness-Aware Meta-Learning via Nash Bargaining." We explore hypergradient conflicts in one-stage meta-learning and their impact on…
      Jupyter Notebook
      •1•4•0•0•Updated May 15, 2024May 15, 2024

    • dataselection

      Public
      Projektor Website
      JavaScript
      •
      MIT License
      •0•0•0•0•Updated Dec 14, 2023Dec 14, 2023

    • projektor

      Public
      This is an official repository for "Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources" (NeurIPS 2023).
      projectionperformance-predictiondata-selection
      projectionperformance-predictiondata-selectionscaling-law
      Python
      •
      MIT License
      •1•14•0•0•Updated Oct 26, 2023Oct 26, 2023

    • privmon

      Public
      This is an official repository for PrivMon: A Stream-Based System for Real-Time Privacy Attack Detection for Machine Learning Models (RAID 2023)
      Python
      •
      MIT License
      •1•4•0•0•Updated Oct 16, 2023Oct 16, 2023

    • CLIP-MIA

      Public
      This is an official repository for Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study (ICCV2023).
      Jupyter Notebook
      •
      MIT License
      •2•25•2•0•Updated Sep 29, 2023Sep 29, 2023

    • 2d-shapley

      Public
      This is an official repository for "2D-Shapley: A Framework for Fragmented Data Valuation" (ICML2023).
      shapleydata-valuation2d-shapley
      shapleydata-valuation2d-shapley
      Jupyter Notebook
      •
      MIT License
      •1•4•1•0•Updated Jul 27, 2023Jul 27, 2023

    • Trojan_Removal_Benchmark

      Public
      Python
      •0•2•0•0•Updated Jul 3, 2023Jul 3, 2023

    • ASSET

      Public
      This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms." ASSET ach…
      aibackdoortransfer-learning
      aibackdoortransfer-learningself-supervised-learningbackdoor-attacksbackdoor-defenseaisecuritybackdoor-detection
      Python
      •
      MIT License
      •0•19•2•0•Updated Jun 7, 2023Jun 7, 2023

    • Narcissus

      Public
      The official implementation of the CCS'23 paper, Narcissus clean-label backdoor attack -- only takes THREE images to poison a face recognition dataset in a clea…
      adversarial-machine-learningadversarial-attacksai-security
      adversarial-machine-learningadversarial-attacksai-securitybackdoor-attacksdeep-poisoning-attacks
      Python
      •
      MIT License
      •15•126•6•0•Updated May 9, 2023May 9, 2023

    • Meta-Sift

      Public
      The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on poisoned dataset.
      ai-securitybackdoor-attacksdata-poisoning
      ai-securitybackdoor-attacksdata-poisoningdataset-security
      Python
      •6•20•0•0•Updated Apr 27, 2023Apr 27, 2023

    • Universal_Pert_Cert

      Public
      This repo is the official implementation of the ICLR'23 paper "Towards Robustness Certification Against Universal Perturbations." We calculate the certified rob…
      Python
      •
      MIT License
      •2•12•0•0•Updated Feb 14, 2023Feb 14, 2023

    • I-BAU

      Public
      Official Implementation of the ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''
      Jupyter Notebook
      •
      MIT License
      •12•2•0•0•Updated Apr 24, 2022Apr 24, 2022

    • frequency-backdoor

      Public
      The official implementation of the ICCV 2021 paper, "Rethinking the backdoor attacks' triggers: A frequency perspective."
      Jupyter Notebook
      •
      MIT License
      •7•1•0•0•Updated Nov 30, 2021Nov 30, 2021

    • Knowledge-Enriched-DMI

      Public
      The official implementation of the ICCV 2021 paper, "Knowledge-Enriched Distributional Model Inversion Attacks."
      Python
      •
      MIT License
      •19•3•0•0•Updated Nov 6, 2021Nov 6, 2021
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.