Deep Leakage from Gradients, Ligeng Zhu, Zhijian Liu, Song Han, 2019Advances in Neural Information Processing Systems (NeurIPS), Vol. 32 (Neural Information Processing Systems Foundation Inc.) - 本文介绍了梯度反演攻击,展示了如何从联邦学习中共享的梯度重建原始数据。
How to backdoor Federated Learning, Eugene Bagdasaryan, Andreas Veit, Yiqing Hua, Deborah Estrin, Vitaly Shmatikov, 2020Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, Vol. 108 (PMLR) - 本文详细介绍了针对联邦学习的实际后门攻击,恶意客户端可将特定漏洞植入全局模型中。