我们重新审视了在人们不信任服务器或其他数据孤岛/客户端的情况下，利用其私有数据进行联邦学习（FL）的问题。在此背景下，每个数据孤岛（例如医院）都拥有来自若干人（例如患者）的数据，并且即使服务器和/或其他数据孤岛试图揭露这些数据，也需要保护每个人数据（例如健康记录）的隐私。孤岛间记录级差分隐私（ISRL-DP）通过要求孤岛 i 的通信满足条目级差分隐私，来防止每个孤岛的数据泄露。先前工作 arXiv:2106.09779 刻画了在同构（i.i.d.）孤岛数据和凸损失函数下，ISRL-DP 算法的最优超额风险界。然而，仍有两个重要问题尚未解决：（1）在异构（non-i.i.d.）孤岛数据下能否实现相同的超额风险界？（2）能否用更少的通信轮数实现最优风险界？本文对这两个问题都给出了肯定回答。我们提出了新颖的 ISRL-DP FL 算法，可在存在异构孤岛数据时实现最优超额风险界。此外，我们的算法比先前最先进方法更具通信效率。对于平滑损失函数，我们的算法实现了最优超额风险界，并且其通信复杂度与非私有下界相匹配。此外，我们的算法比先前最先进方法更具计算效率。
英文摘要：
We revisit the problem of federated learning (FL) with private data from people who do not trust the server or other silos/clients. In this context, every silo (e.g. hospital) has data from several people (e.g. patients) and needs to protect the privacy of each person's data (e.g. health records), even if the server and/or other silos try to uncover this data. Inter-Silo Record-Level Differential Privacy (ISRL-DP) prevents each silo's data from being leaked, by requiring that silo i's communications satisfy item-level differential privacy. Prior work arXiv:2106.09779 characterized the optimal excess risk bounds for ISRL-DP algorithms with homogeneous (i.i.d.) silo data and convex loss functions. However, two important questions were left open: (1) Can the same excess risk bounds be achieved with heterogeneous (non-i.i.d.) silo data? (2) Can the optimal risk bounds be achieved with fewer communication rounds? In this paper, we give positive answers to both questions. We provide novel ISRL-DP FL algorithms that achieve the optimal excess risk bounds in the presence of heterogeneous silo data. Moreover, our algorithms are more communication-efficient than the prior state-of-the-art. For smooth loss functions, our algorithm achieves the optimal excess risk bound and has communication complexity that matches the non-private lower bound. Additionally, our algorithms are more computationally efficient than the previous state-of-the-art.
Robust Federated Learning under Adversarial Attacks via Loss-Based Client Clustering
School of Electrical and Computer Engineering, National Technical University of Athens（电气与计算机工程学院，国家技术大学雅典）；Faculty of Sciences, University of Novi Sad（科学学院，诺维萨德大学）
FedGreed: A Byzantine-Robust Loss-Based Aggregation Method for Federated Learning
School of Electrical and Computer Engineering（电气与计算机工程学院）；National Technical University of Athens（雅典技术大学）；Department of Mathematics and Informatics（数学与信息学系）；Faculty of Sciences, University of Novi Sad（自然科学学院，诺维萨德大学）
Robust and Actively Secure Serverless Collaborative Learning
Northwestern University（西北大学）；CISPA（CISPA亥姆霍兹信息安全中心）；Google（谷歌）；University of Toronto and Vector Institute（多伦多大学与向量研究所）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
FedLNS: Leverage LayerNorm Signature Modeling to Mitigate Adversarial Manipulation in Federated LLMs
Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg（卢森堡大学安全、可靠性与跨学科研究中心（SnT））；Carnegie Mellon University（卡内基梅隆大学）；Edith Cowan University（埃迪斯科文大学）；TU Berlin（柏林工业大学）
