# gradient-poisoning
標記為「gradient-poisoning」的 2 篇文章
Federated Learning Poisoning (Training Pipeline)
Federated learning architecture vulnerabilities: Byzantine attacks, model replacement, gradient manipulation, and techniques for poisoning global models through malicious participants.
federated-learningbyzantinemodel-replacementgradient-poisoningaggregationprivacy
聯邦學習投毒（訓練管線）
聯邦學習架構漏洞：Byzantine 攻擊、模型替換、梯度操弄，以及經由惡意參與者投毒全域模型之技術。
federated-learningbyzantinemodel-replacementgradient-poisoningaggregationprivacy