In federated news recommendation, representing each news with a single embedding entangles shared semantics with user-specific preference shifts, which weakens personalization under non-IID users and strains communication when catalogs are large. To address this problem, we introduce FedDEN, a Dual News-Embedding framework that cleanly disentangles the two roles of item representation: a server-maintained global embedding captures cross-user semantics, while a lightweight client residual captures user-dependent deviations only where needed. Based on this core and tailored to the peculiarities of news recommendation, we attach two targeted mechanisms: (i) a minimal cold-start bias that substitutes residuals when histories are scarce, enabling immediate participation without extra rounds; and (ii) an alignment-and-sparsity regularization that keeps residuals complementary to the global table while promoting a compact, communicable global news embedding via proximal updates. Experiments on three real world datasets show consistent gains over strong centralized and federated baselines on metrics, together with robust behavior under cold-start settings, and favorable per-round communication. By solving the conflation of shared semantics and user-specific shifts at its source, FedDEN achieves strong personalization with practical efficiency. Specifically, it outperforms centralized baseline NRMS by 13.61 % and FedRec by 15.59 %.

Fast Gradient Sign Method (FGSM)-based ap proaches play a critical role in adversarial attacks, particularly in transfer-based attacks. Recent advancements aim to enhance adversarial transferability by refining the sign function in FGSMs using precise gradient information. However, due to the instability of gradient update directions, such precise gradient information may still converge to local minima, thereby limiting transferability. To address this issue, we propose Majority-vote Gradient Scaling (MVGS), a novel method designed to sta bilize gradient update directions. MVGS dynamically rescales momentum terms by evaluating the consistency of historical gradients at each pixel. Since MVGS operates solely through parameter-specific momentum rescaling, it can be seamlessly integrated with existing adversarial attack methods that lever age precise gradient information. Extensive comparative and ablation experiments demonstrate that MVGS significantly improves attack success rates (ASR), achieving up to a 6.1% increase over the state-of-the-art APAA method, confirming its effectiveness.

Federated Learning enables multiple clients to collaboratively train a model without sharing their individual data, thereby protecting local data privacy. However, attackers, such as untrusted servers, can still compromise the privacy of clients’ local training data through various inference attacks. One feasible approach to protect client privacy during training is the incorporation of differential privacy. Nevertheless, achieving an ideal level of privacy protection with differential privacy often degrades the model’s performance, significantly reducing its accuracy. To enhance model accuracy while minimizing the additional client heterogeneity introduced by differential privacy, this paper proposes a method that integrates personalized layers and data transformations, FusTP-FL. The core of our FusTP-FL is the incorporation of personalized layers and personalized data transformations within the client’s local training model, which further reduces client heterogeneity and improves model accuracy. We evaluated the model’s accuracy on six common datasets; experimental results demonstrate that the proposed FusTP-FL effectively enhances model accuracy across two different differential privacy modes (CDP and LDP), increasing it by up to 45%. Furthermore, we show that compared to PRIVATEFL, our method achieves lower client heterogeneity.

Abstract Photos or videos taken by individuals often carry sensitive details such as facial identities, which has led to an escalating societal interest in privacy protection measures. We suggest an improved face identity transformer that offers password-protected anonymization and de-anonymization of photo-realistic facial images in visual data. Our face identity transformer is designed to (1) erase facial identity information after anonymization, (2) restore the original face when a correct password is provided and (3) generate an incorrect but realistic face when given an incorrect password. The processes of image anonymization and de-anonymization are facilitated through a password scheme, a multi-task learning objective and generative adversarial networks comprising InfoGAN and contrastive learning. In-depth experiments indicate that our methodology can execute anonymization and de-anonymization based on password conditions whilst reducing training time and enhancing image quality compared to existing anonymization procedures. Additionally, it maintains a recognition rate as low as 4.8% for anonymized images without sacrificing the face detection rate of the original method.

Communication overhead is a significant challenge in distributed deep learning (DDL) training, often hindering efficiency. While existing solutions like gradient compression, compute/communication overlap, and layer-wise flow scheduling have been proposed, they are often coarse-grained and insufficient, especially under network congestion. These congestion-unaware methods can lead to long flow completion times, known as the tail latency, resulting in extended training time. In this paper, we argue that packet loss tolerance methods can mitigate the tail latency issue without sacrificing training accuracy, with the tolerance bound varying across different DDL model layers. We introduce PLOT, a fine-grained packet loss tolerance algorithm, which optimizes communication overhead by leveraging the layer-specific loss tolerance of the DNN model. PLOT employs a UDP-based transmission mechanism for gradient transfer, addressing the tail latency issue and maintaining training accuracy through packet loss tolerance. Our evaluations on both small-scale testbeds and large-scale simulations show that PLOT outperforms other congestion algorithms, effectively reducing tail latency and DDL training time.

The rapid development of current data centers and Industrial Internet of Things has brought about the explosive growth of information, which leads to the need for better performance of cluster communication systems. Coflow scheduling has the potential to enhance communication performance among applications in data parallel clusters. However, current coflow scheduling techniques that lack preliminary knowledge often depend on a fixed set of threshold parameters within a multilevel feedback queue (MLFQ), disregarding network variability. Though manually tweaking threshold settings may support network flexibility, it negatively impacts real-time performance and increases workload. Furthermore, manual threshold adjustments often fail to react promptly and adaptively to network environmental changes. To address the issues highlighted above, this paper presents D-MLFQ, a novel approach that leverages deep reinforcement learning to dynamically and autonomously regulate the threshold of MLFQ. As a result, D-MLFQ offers enhanced scheduling and communication optimization capabilities. Furthermore, the study performs trace-driven simulations to assess the efficacy of D-MLFQ. Empirical data indicate that D-MLFQ outperforms Aalo, which utilizes fixed threshold, by up to 1.39× in terms of coflow’s completion time. Compared to other common scheduling algorithms such as per-flow fairness, D-MLFQ achieves up to 2.13× faster completion time.

The swift advancement of distributed computing has enhanced the support for big data and massive-scale models. Yet, delivering superior services to manage large and intricate network flows in data center networks remains a formidable challenge. In this paper, we present ReQ-tank, an intricate flow scheduling approach based on a multi-level feedback queue (MLFQ) devised to achieve flow prioritization and efficient flow scheduling. ReQ-tank employs a two-tier scheduling strategy: On the flow scheduling layer, priority queues are segmented into two categories, and the flows within high-priority queues follow a strict priority scheduling, while those in low-priority queues adhere to differential weighted Round-robin scheduling; On the packet scheduling layer, ReQ-tank modifies the priority of initially high-priority re-transmitted packets to facilitate fine-grained data packet scheduling. We carry out simulation experiments on web search workloads and data mining workloads. Experimental results demonstrate that ReQ-tank can curtail packet wait time in the network, significantly truncate the flow completion time (FCT) of delay-sensitive flows and counteract the issue of flow starvation in traditional strict priority queues. Consequently, ReQ-tank is deemed more suitable for complex distributed network applications.

Federated Learning has been widely used due to its ability to train models while ensuring data privacy and security. However, the presence of non-i.i.d. (independent and identically distributed) data among different participating entities leads to significant performance disparities in Federated Learning. In addition, as the essence of Federated Learning involves model training on local devices without centralized data storage, it poses certain challenges in personalized tasks. Traditional centralized machine learning methods can perform deep learning and personalized model training on centralized data, while distributed data in Federated Learning may not provide enough information to support personalized requirements. In this paper, we propose a personalized Federated Learning method called FedFC, which adopts parameter decoupling to address the data domain shift issue in Federated Learning. We experimentally validate our proposed solutions on the OrganCMNIST and COVID-19 datasets. The experimental results show that compared to existing methods, FedFC achieves average accuracy improvements of 4.93% and 6.31% on the two datasets, respectively. Additionally, by employing partial gradient uploading, we successfully reduce the communication overhead by 22.67% and 26.91% for each dataset.

Industrial Internet of Things (IIoT) is the leading application scenario of the fifth generation wireless communication systems (5G) and beyond. Nonorthogonal multiple access (NOMA) has become a key technology for 5G due to its high spectrum efficiency. In this article, a joint channel and power resource allocation problem is investigated for cross-cell IIoT networks with aim of maximizing sum rate of NOMA-based machine-to-machine pairs and cellular Machine Devices (cMDs). Since joint channel and power resource allocation problem is an NP-hard problem, the original problem is transformed into a hypergraph model to optimize channel and power resource allocation. Then, a channel allocation algorithm based on hypergraph coloring theory is proposed, and an alternative power allocation algorithm is presented. Next, some properties of hypergraph coloring and complexities are analyzed. Finally, simulation results demonstrate that the proposed algorithm outperforms the graph-based algorithm in terms of sum rate, and also improves the spectrum efficiency significantly.

Federated learning enables local nodes to train a global model together by uploading only training updates to the parameter server without exchanging private data. However, as the complexity of the federated learning task increases, the communication volume of the training process becomes extremely large, hence the huge communication traffic becomes a serious bottleneck in current federated learning application. Existing methods reduce communication overhead from two aspects, the number of communications and the traffic per communication. But these methods usually lead to more consumption of computing resources or a decrease in model accuracy. To handle these problems, this paper proposes a data fitting based weight compression algorithm, FWC, which includes four sequential stages: sparsification, polynomial fitting, encoding, reconstruction and two mechanism: warm-up and accumulation. In particular, the warm-up mechanism can well address the problem of slow convergence in early training period. Experimental results on models with different scales show that FWC is able to provide more than 600x traffic compression at the cost of only millisecond-level computational time cost and less than 1% accuracy loss.

Today, cloud storage becomes one of the critical services, because users can easily modify and share data with others in cloud. However, the integrity of shared cloud data is vulnerable to inevitable hardware faults, software failures or human errors. To ensure the integrity of the shared data, some schemes have been designed to allow public verifiers (i.e., third party auditors) to efficiently audit data integrity without retrieving the entire users’ data from cloud. Unfortunately, public auditing on the integrity of shared data may reveal data owners’ sensitive information to the third party auditor. In this paper, we propose a new privacy-aware public auditing mechanism for shared cloud data by constructing a homomorphic verifiable group signature. Unlike the existing solutions, our scheme requires at leasttgroup managers to recover a trace key cooperatively, which eliminates the abuse of single-authority power and provides non-frameability. Moreover, our scheme ensures that group users can trace data changes through designated binary tree; and can recover the latest correct data block when the current data block is damaged. In addition, the formal security analysis and experimental results indicate that our scheme is provably secure and efficient.

Edge computing is emerging as an innovative technology that brings data processing and storage to end users, further leading to scale, decentralization and safety to IoT netWorks. It improves the quality of services but meanwhile introduces great challenges such as data security, latency, etc. Fortunately, blockchain technology can improve security issues of edge computing in IoT networks as it alloWs only trusted IoT nodes to interact With each other. To better address the security risks of data sharing problem and improve the credibility of data, this paper presents a Blockchain and Edge computing Assistant security FrameWork (BEAF) With data sharing for IoT netWorks. With blockchain and edge computing, BEAF supports both decentralization and data tracing after data sharing. In addition, BEAF can achieve access control and share data to specific node. We also conduct security analysis and shoiv that BEAF provides confidentiality, availability, data integrity, etc. In addition, We develop the base layer through Hyperledger Fabric technology, and evaluate the performance of BEAF in terms of stability, scalability and efficiency.

Side-channel analysis (SCA) is usually used for analyzing the side-channel resistance of a crypto device. However, it does not mean “practical secure” when a SCA attack fails since SCA only provides a success or failure conclusion. On the basis of the SCA data about scores and ranks of all candidates for each subkey, it is still possible to apply key enumeration (KE) algorithms to search the correct master key at an affordable overhead. Nevertheless, the efficiency of KE is limited by the SCA data in essence. To address the issue, we proposed two methods to exploit the SCA data and Riemann integral of the rank curves of all subkey candidates to update each correct sub key rank before carrying out KE. We applied the proposed methods for different crypto implementations running on different devices to verify their performance. Experimental studies for both mono-channel and multi-channel leakages verified that the proposed methods were effective in improving the efficiency of KE to recover the correct key. The proposed methods are designed for processing the SCA data and can be deemed as a preliminary before executing KE. The work of this paper bridges the gap between SCA and KE.