Federated learning (FL) enables a set of geographically distributed clients
to collectively train a model through a server. Classically, the training
process is synchronous, but can be made asynchronous to maintain its speed in
presence of slow clients and in heterogeneous networks. The vast majority of
Byzantine fault-tolerant FL systems however rely on a synchronous training
process. Our solution is one of the first Byzantine-resilient and asynchronous
FL algorithms that does not require an auxiliary server dataset and is not
delayed by stragglers, which are shortcomings of previous works. Intuitively,
the server in our solution waits to receive a minimum number of updates from
clients on its latest model to safely update it, and is later able to safely
leverage the updates that late clients might send. We compare the performance
of our solution with state-of-the-art algorithms on both image and text
datasets under gradient inversion, perturbation, and backdoor attacks. Our
results indicate that our solution trains a model faster than previous
synchronous FL solution, and maintains a higher accuracy, up to 1.54x and up to
1.75x for perturbation and gradient inversion attacks respectively, in the
presence of Byzantine clients than previous asynchronous FL solutions.

通过无需辅助服务器数据集并且不受落后节点限制的拜占庭容错和异步联邦学习算法，我们的解决方案可以更快地训练模型，在梯度反转攻击下最多能保持 1.54 倍准确率，而在扰动攻击下最多能保持 1.75 倍准确率。

非同步拜占庭联邦学习

Asynchronous Byzantine Federated Learning

In this paper, we propose an iterative scheme for distributed
Byzantineresilient estimation of a gradient associated with a black-box model.
Our algorithm is based on simultaneous perturbation, secure state estimation
and two-timescale stochastic approximations. We also show the performance of
our algorithm through numerical experiments.

本文提出分布式迭代方案，用于对与黑箱模型相关的梯度进行拜占庭容错评估，基于同时扰动、安全状态评估和双时间尺度随机逼近，同时通过数值实验展示了算法性能。

在线多智能体去中心化拜占庭容错梯度估计

Online Multi-Agent Decentralized Byzantine-robust Gradient Estimation

Secure federated learning is a privacy-preserving framework to improve
machine learning models by training over large volumes of data collected by
mobile users. This is achieved through an iterative process where, at each
iteration, users update a global model using their local datasets. Each user
then masks its local model via random keys, and the masked models are
aggregated at a central server to compute the global model for the next
iteration. As the local models are protected by random masks, the server cannot
observe their true values. This presents a major challenge for the resilience
of the model against adversarial (Byzantine) users, who can manipulate the
global model by modifying their local models or datasets. Towards addressing
this challenge, this paper presents the first single-server Byzantine-resilient
secure aggregation framework (BREA) for secure federated learning. BREA is
based on an integrated stochastic quantization, verifiable outlier detection,
and secure model aggregation approach to guarantee Byzantine-resilience,
privacy, and convergence simultaneously. We provide theoretical convergence and
privacy guarantees and characterize the fundamental trade-offs in terms of the
network size, user dropouts, and privacy protection. Our experiments
demonstrate convergence in the presence of Byzantine users, and comparable
accuracy to conventional federated learning benchmarks.

本文提出了首个单服务器拜占庭容错安全的聚合框架（BREA）用于安全联邦学习，包括完整的隐私保护和网络收敛保证，基于综合随机量化、可验证的异常检测和安全的模型聚合方法，并对网络规模、用户退化和隐私保护方面进行了理论和实验分析。