Skip to content
@ruoxi-jia-group

ReDS Lab

Responsible Data Science Lab @ Virginia Tech | AI Security & Privacy & More

Pinned

  1. Narcissus 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 clean-label way and achieves a 99.89% att…

    Python 92 10

  2. LAVA LAVA Public

    This is an official repository for "LAVA: Data Valuation without Pre-Specified Learning Algorithms" (ICLR2023).

    Python 37 7

  3. Meta-Sift 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.

    Python 14 4

  4. Universal_Pert_Cert 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 robustness against universal perturbatio…

    Python 12 2

  5. ASSET ASSET Public

    This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms." ASSET achieves state-of-the-art reliability in …

    Python 14

  6. CLIP-MIA 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 13 2

Repositories

Showing 10 of 15 repositories
  • LAVA Public

    This is an official repository for "LAVA: Data Valuation without Pre-Specified Learning Algorithms" (ICLR2023).

    Python 37 MIT 7 2 1 Updated May 18, 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 fairness. Our two-stage approach uses Nash bargaining to mitigate conflicts, enhancing fairness and model performance simultaneously.

    Jupyter Notebook 0 0 0 0 Updated May 15, 2024
  • dataselection Public

    Projektor Website

    JavaScript 0 MIT 0 0 0 Updated Dec 14, 2023
  • projektor Public

    This is an official repository for "Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources" (NeurIPS 2023).

    Python 8 MIT 1 0 0 Updated Oct 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 3 MIT 0 0 0 Updated Oct 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 13 MIT 2 1 0 Updated Sep 29, 2023
  • 2d-shapley Public

    This is an official repository for "2D-Shapley: A Framework for Fragmented Data Valuation" (ICML2023).

    Jupyter Notebook 3 MIT 1 1 0 Updated Jul 27, 2023
  • Trojan_Removal_Benchmark Public
    Python 2 0 0 0 Updated Jul 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 achieves state-of-the-art reliability in detecting poisoned samples in end-to-end supervised learning/ self-supervised learning/ transfer learning.

    Python 14 MIT 0 2 0 Updated Jun 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 clean-label way and achieves a 99.89% attack success rate.

    Python 92 MIT 10 5 (1 issue needs help) 0 Updated May 9, 2023
View all repositories

Top languages

Loading…

Most used topics

Loading…