shaneson0 / attacking_federate_learning

基于《A Little Is Enough: Circumventing Defenses For Distributed Learning》的联邦学习攻击模型

Federate Learning 攻防复现篇

更新日期截止2020年5月22日，项目定期维护和更新，维护各种SOTA的Federated Learning的攻防模型。(更新中。。）

论文 (Defend)

1. (Krum): Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent【NIPS 2017】
2. (trimmed_mean): D. Yin, Y. Chen, K. Ramchandran, and P. Bartlett. Byzantine-robust distributed learning: Towards optimal statistical rates. In Proceedings of the International Conference on Machine Learning (ICML), 2018.
3. (bulyan): E. M. El Mhamdi, R. Guerraoui, and S. Rouault. The hidden vulnerability of distributed learning in Byzantium. In Proceedings of the 35th International Conference on Machine Learning (ICML), pages 3521–3530, 2018.

---

论文 (Attack)

4. A Little Is Enough: Circumventing Defenses For Distributed Learning【NIPS 2019】

代码运行

mkdir logs
python main.py

attacking_federate_learning's Issues

实验问题

大佬您好，我用您程序跑实验，无法达到论文中的效果，请问哪里可能出了问题