YiZeng623
Follow
Highlights
- Pro
-
DecodingTrust Public
Forked from AI-secure/DecodingTrustA Comprehensive Assessment of Trustworthiness in GPT Models
Python Creative Commons Attribution Share Alike 4.0 International UpdatedMar 2, 2024 -
-
Universal_Pert_Cert Public
Forked from reds-lab/Universal_Pert_CertThis 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 MIT License UpdatedFeb 11, 2023 -
I-BAU Public
Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''
-
cvpr-latex-template Public
Forked from apoorvkh/cvpr-latex-templateExtended LaTeX template for CVPR/ICCV papers
TeX UpdatedOct 11, 2022 -
Meta-Sift Public
Forked from reds-lab/Meta-SiftThe official implementation of Meta-Sift -- Ten minutes or less to find a 1000-size or larger clean subset on any poisoned dataset.
Python MIT License UpdatedAug 29, 2022 -
BackdoorBox Public
Forked from THUYimingLi/BackdoorBoxPython GNU General Public License v2.0 UpdatedMay 14, 2022 -
frequency-backdoor Public
ICCV 2021, We find most existing triggers of backdoor attacks in deep learning contain severe artifacts in the frequency domain. This Repo. explores how we can use these artifacts to develop strong…
-
Narcissus-backdoor-attack Public
Forked from reds-lab/NarcissusThe official implementation of 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 MIT License UpdatedApr 12, 2022 -
-
NAD Public
Forked from bboylyg/NADThis is an implementation demo of the ICLR 2021 paper [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://openreview.net/pdf?id=9l0K4OM-oXE) in PyTorch.
Python UpdatedJan 18, 2022 -
Official implementation of the IEEE TII paper: 'Adaptive Backdoor Trigger Detection in Edge-Deployed DNNs in 5G-Enabled IIoT Systems'
MIT License UpdatedAug 21, 2021 -
backdoor-learning-resources Public
Forked from THUYimingLi/backdoor-learning-resourcesA curated list of backdoor learning resources
MIT License UpdatedDec 15, 2020 -
DeepSweep Public
An evaluation framework for mitigating DNN backdoor attacks using data augmentations
-
FenceBox Public
The official FenceBox Platform -- implementation of paper:' FenceBox A Platform for Defeating Adversarial Examples with Data Augmentation Techniques.'
-
requirements Public template
Forked from binder-examples/requirementsSimple requirements.txt based example
Jupyter Notebook BSD 3-Clause "New" or "Revised" License UpdatedSep 8, 2020 -
Take further steps in the arms race of adversarial examples with only preprocessing.