The decentralized nature of federated learning (FL) makes it difficult to verify the trustworthiness of participating clients, creating an opportunity for backdoor attacks. This paper addresses a general backdoor-resilient decentralized FL problem without any prior knowledge of the type of backdoor attacks or information about malicious clients. After an in-depth investigation of how backdoor attacks are conducted in FL, we introduce a multi-armed bandit-based knowledge distillation approach to help benign clients learn useful knowledge from other clients while rejecting potential backdoors hidden in shared updates. Unlike most previous works that rely on identifying and removing malicious updates—an approach limited to scenarios with fewer than 50% attackers—our knowledge distillation technique enables benign clients to reject backdoored knowledge while preserving useful information, maintaining effective defense even when malicious clients exceed 50% of the population. Additionally, to handle the various updates from clients with Non-IID dataset, a multi-armed bandit scheme is designed for each benign client to select the most appropriate teachers for knowledge distillation, resulting in high accuracy and fast convergence. Extensive experiments demonstrate that our multi-armed bandit-based knowledge distillation approach achieves high accuracy and general backdoor resilience. Comparisons with previous works show that our approach can reduce the attack success rate by 14.71%∼96.78% on average.

As a combination of digital twin and edge computing, the digital twin edge networks (DITENs) have gained significant interest due to their bridging roles between physical edge networks and digital systems. The Device-to-Device (D2D) communication acts as an ongoing transmission paradigm for DITENs since it facilitates interoperability between nearby wireless entities and enhances the spectrum utilization and overall throughput via direct link. However, most existing works on the D2D communication are related to the centralized ones, and consider the mobility and interference management separately, which cannot be used for the dynamic scenarios in DITENs. In this paper, we consider the D2D communication problem in dynamic DITENs in the context of the SINR model, and propose a dynamicity-tolerant D2D communication algorithm in a distributed manner. Using an oblivious transmission strategy, our algorithm can complete the D2D communication among$n$entities within$O(\log n)$time steps despite the various dynamic factors, which achieves asymptotically optimal time complexity. It is asserted that the D2D communication algorithm is asymptotically optimal, given that the lower bound for successful message dissemination is$\Omega (\log n)$. Rigorous theoretical analyses and empirical results are conducted to show the correctness and efficiency of our proposed algorithm.

Meta computing, as an innovative computing paradigm, aims to transform the Internet into a vast and distributed computing resource pool. This paradigm holds significant promise for the Industrial Internet of Things (IIoT), offering efficient, fault-tolerant, and personalized services while ensuring strong security and privacy. Nowadays, content delivery networks (CDNs) are integral to this vision, providing critical network support by reducing latency, alleviating network congestion, and enhancing service quality. Accurate prediction of CDN cache group performance, which involves heterogeneous edge servers handling diverse workloads, is essential for optimal resource utilization, dynamic load balancing, and efficient traffic management in IIoT. This article addresses the challenge of performance prediction in CDNs using machine learning techniques. By leveraging business request data, load information, and other relevant features, our approach aims to predict key performance indicators, such as CPU utilization, bandwidth usage, and I/O operations. We propose a comprehensive feature engineering method that aggregates input metrics across devices, categorizes business requests using clustering, and incorporates time series modeling to capture traffic patterns. Extensive experiments demonstrate the effectiveness of our approach, highlighting its potential to enhance resource management and service quality in CDNs, thereby supporting the deployment of meta computing in IIoT.

Due to its decentralized framework and outdoor environments, federated edge learning (FEEL) faces significant vulnerability to malicious attacks within edge networks. Prevailing FEEL approaches typically hinge on a dependable parameter server (PS) to contend with the adversarial updates from Byzantine clients. Recognizing the inherent unreliability of PSs in edge networks, this paper delves into the security challenges of FEEL, specifically addressing Byzantine PSs. We present a Byzantine fault-tolerant FEEL algorithm, named Fed-MS, in which a multi-server technique along with a newly designed trimmed-mean-based model filter is employed. This combination ensures that each client can obtain a feasible global model for its local training, closely approximating a true model aggregated by benign PSs. Furthermore, we propose a sparse uploading strategy in Fed-MS to enhance communication efficiency for model aggregation to multiple PSs. Theoretical analysis demonstrates that, when Byzantine PSs are a minority, Fed-MS achieves an expected convergence speed of$O(1/T)$with$T$defined as the number of training rounds, akin to state-of-the-art works under non-Byzantine settings. Extensive experiments are conducted on the CIFAR-10 dataset with MobileNet V2 as the training model. The numerical results show that our Fed-MS can improve the model accuracy from 10% to at least 76% under the malicious attacks from Byzantine PSs. Our code is released at https://github.com/haoma2772/Fed-MS.