Depriving the Survival Space of Adversaries Against Poisoned Gradients in Federated Learning

[PDF] arxiv.org

DarkFed: A Data-Free Backdoor Attack in Federated Learning

M Li, W Wan, Y Ning, S Hu, L Xue, LY Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
Federated learning (FL) has been demonstrated to be susceptible to backdoor attacks.
However, existing academic studies on FL backdoor attacks rely on a high proportion of real …
被引用次数：4 相关文章 所有 2 个版本