期刊
NEURAL NETWORKS
卷 169, 期 -, 页码 756-763出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2023.10.034
关键词
Clean-label poisoning attacks; Transfer learning; Robust foundation model
We propose a defense strategy that reduces the success rate of data poisoning attacks in downstream tasks by pre-training a robust foundation model.
In the transfer learning paradigm, models that are pre-trained on large datasets are used as the foundation models for various downstream tasks. However, this paradigm exposes downstream practitioners to data poisoning threats, as attackers can inject malicious samples into the re-training datasets to manipulate the behavior of models in downstream tasks. In this work, we propose a defense strategy that significantly reduces the success rate of various data poisoning attacks in downstream tasks. Our defense aims to pre-train a robust foundation model by reducing adversarial feature distance and increasing inter-class feature distance. Experiments demonstrate the excellent defense performance of the proposed strategy towards state-of-the-art clean-label poisoning attacks in the transfer learning scenario.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据