ReDS Lab

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

PinnedLoading

NarcissusNarcissusPublic
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 110 13
LAVALAVAPublic
This is an official repository for "LAVA: Data Valuation without Pre-Specified Learning Algorithms" (ICLR2023).
Python 47 7
Meta-SiftMeta-SiftPublic
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 18 5
Universal_Pert_CertUniversal_Pert_CertPublic
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
ASSETASSETPublic
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 17
CLIP-MIACLIP-MIAPublic
This is an official repository for Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study (ICCV2023).
Jupyter Notebook 22 1

Repositories

Showing 10 of 22 repositories

reds-lab.github.io Public
Homepage portfolio of Reds Projects
reds-lab/reds-lab.github.io’s past year of commit activity
TypeScript0MIT0 0 0 UpdatedFeb 11, 2025
Restricted_gradient_diversity_unlearning Public
reds-lab/Restricted_gradient_diversity_unlearning’s past year of commit activity
Python 40 1 0 UpdatedDec 16, 2024
preference-learning-with-rationales Public
This is the public repository for Data-Centric Human Preference Optimization with Rationales.
reds-lab/preference-learning-with-rationales’s past year of commit activity
Python 2Apache-2.00 0 0 UpdatedJul 22, 2024
WokeyTalky Public
reds-lab/WokeyTalky’s past year of commit activity
HTML 20 0 0 UpdatedJul 12, 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".
reds-lab/BEEAR’s past year of commit activity
HTML 15 1 0 0 UpdatedJul 3, 2024
Forward-INF Public
reds-lab/Forward-INF’s past year of commit activity
Jupyter Notebook 4Apache-2.00 0 0 UpdatedJun 20, 2024
Woke-Pipeline Public
reds-lab/Woke-Pipeline’s past year of commit activity
Python0MIT0 0 0 UpdatedJun 14, 2024
LAVA Public
This is an official repository for "LAVA: Data Valuation without Pre-Specified Learning Algorithms" (ICLR2023).
reds-lab/LAVA’s past year of commit activity
Python 47MIT 7 2 1 UpdatedJun 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 fairness. Our two-stage approach uses Nash bargaining to mitigate conflicts, enhancing fairness and model performance simultaneously.
reds-lab/Nash-Meta-Learning’s past year of commit activity
Jupyter Notebook 40 0 0 UpdatedMay 15, 2024
dataselection Public
Projektor Website
reds-lab/dataselection’s past year of commit activity
JavaScript0MIT0 0 0 UpdatedDec 14, 2023