ReDS Lab
Change the repository type filter
All
Repositories list
21 repositories
- This is an official repository for "LAVA: Data Valuation without Pre-Specified Learning Algorithms" (ICLR2023).
- 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.
- This is an official repository for "Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources" (NeurIPS 2023).
privmon
PublicCLIP-MIA
Public2d-shapley
PublicThis is an official repository for "2D-Shapley: A Framework for Fragmented Data Valuation" (ICML2023).Trojan_Removal_Benchmark
PublicASSET
PublicThis 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.Narcissus
PublicThe 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.Meta-Sift
PublicThe 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.Universal_Pert_Cert
PublicI-BAU
Publicfrequency-backdoor
PublicKnowledge-Enriched-DMI
Public