arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.01409cs.LG
收藏

理解神经网络的联邦学习的质量挑战:从鲁棒性角度的初步观察

Towards Understanding Quality Challenges of the Federated Learning for Neural Networks: A First Look from the Lens of Robustness

University of Calgary(卡尔加里大学);Technical University of Munich(慕尼黑工业大学);University of Alberta(阿尔伯塔大学);York University(约克大学)

Amin Eslami Abyane, Derui Zhu, Roberto Souza, Lei Ma, Hadi Hemmati

摘要:

联邦学习(FL)是一种分布式学习范式,它在利用所有参与者的整个数据集的同时保护用户的数据隐私。在FL中,多个模型在客户端上独立训练,并集中聚合,以在迭代过程中更新全局模型。虽然这种方法在保护隐私方面非常出色,但FL仍然存在质量问题,例如攻击或拜占庭故障。最近的尝试已经解决了强大的聚合技术FL的质量挑战。然而,国家的最先进的(SOTA)强大的FL技术的有效性仍然不清楚,缺乏一个全面的研究。因此,为了更好地了解这些SOTA FL技术在存在攻击和故障的情况下的当前质量状况和挑战,我们进行了大规模的实证研究,从攻击、模拟故障(通过突变算子)和聚合(防御)方法的多个角度调查SOTA FL的质量。特别是,我们研究了FL在图像分类任务上的性能,并使用DNN作为我们的模型类型。此外,我们对两个通用图像数据集和一个真实世界的联邦医学图像数据集进行了研究。我们还研究了受影响的客户端的比例和数据集分布因素对FL的鲁棒性的影响。在对496个配置进行大规模分析后,我们发现每个用户上的大多数mutator对通用数据集中的最终模型的影响可以忽略不计,并且其中只有一个在医疗数据集中是有效的。此外,我们表明,模型中毒攻击比数据投毒攻击更有效。此外,选择最强大的FL聚合器取决于攻击和数据集。最后,我们说明了一个简单的集成聚合器实现了一个更强大的解决方案比任何单一的聚合器,是最好的选择,在75%的情况下。

英文摘要:

Federated learning (FL) is a distributed learning paradigm that preserves users' data privacy while leveraging the entire dataset of all participants. In FL, multiple models are trained independently on the clients and aggregated centrally to update a global model in an iterative process. Although this approach is excellent at preserving privacy, FL still suffers from quality issues such as attacks or byzantine faults. Recent attempts have been made to address such quality challenges on the robust aggregation techniques for FL. However, the effectiveness of state-of-the-art (SOTA) robust FL techniques is still unclear and lacks a comprehensive study. Therefore, to better understand the current quality status and challenges of these SOTA FL techniques in the presence of attacks and faults, we perform a large-scale empirical study to investigate the SOTA FL's quality from multiple angles of attacks, simulated faults (via mutation operators), and aggregation (defense) methods. In particular, we study FL's performance on the image classification tasks and use DNNs as our model type. Furthermore, we perform our study on two generic image datasets and one real-world federated medical image dataset. We also investigate the effect of the proportion of affected clients and the dataset distribution factors on the robustness of FL. After a large-scale analysis with 496 configurations, we find that most mutators on each user have a negligible effect on the final model in the generic datasets, and only one of them is effective in the medical dataset. Furthermore, we show that model poisoning attacks are more effective than data poisoning attacks. Moreover, choosing the most robust FL aggregator depends on the attacks and datasets. Finally, we illustrate that a simple ensemble of aggregators achieves a more robust solution than any single aggregator and is the best choice in 75% of the cases.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑