Pinned Loading

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 122 15

2. LAVA LAVA Public

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

   Python 52 8

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 20 6

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 19

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 24 1