ECLIPSE: Expunging Clean-Label Indiscriminate Poisons via Sparse Diffusion Purification
- 5 September 2024
- book chapter
- Published by Springer Nature
- p. 146-166
Abstract
No abstract availableKeywords
All Related Versions
This publication has 20 references indexed in Scilit:
- CUDA: Convolution-Based Unlearnable Datasets2023
- Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency2023
- FedDPGAN: Federated Differentially Private Generative Adversarial Networks Framework for the Detection of COVID-19 PneumoniaInformation Systems Frontiers, 2021
- Shortcut learning in deep neural networksNature Machine Intelligence, 2020
- Applied Stochastic Differential Equations2019
- TensorClog: An Imperceptible Poisoning Attack on Deep Neural Network ApplicationsIEEE Access, 2019
- UNet++: A Nested U-Net Architecture for Medical Image Segmentation2018
- Densely Connected Convolutional Networks2017
- Deep Residual Learning for Image Recognition2016
- ImageNet: A large-scale hierarchical image database2009