Concurrency and Computation-Practice & Experience最新文献

{"title":"MOFDRNet: A Model for Data Leakage Attacks in Federated Learning","authors":"Yaru Zhao,&nbsp;Jianbiao Zhang,&nbsp;Yihao Cao,&nbsp;Xianqun Han","doi":"10.1002/cpe.70032","DOIUrl":"https://doi.org/10.1002/cpe.70032","url":null,"abstract":"<div>\u0000 \u0000 <p>Federated Learning allows multiple clients to train local models and aggregate them on the server side. The client is invisible to the shared global model generated by the server, which provides an opportunity for malicious attackers to utilize the inherent vulnerability of federated learning to initiate data leakage attacks. Existing attack techniques are largely <i>client-based</i> and focus on <i>inferring model parameters directly</i>, but do not work for server-based attacks, mainly due to differences in their ability to generalize attacks. Yet few robust data leakage attacks toward federated learning vulnerability have been developed on the server side. To address the above problem, we propose MOFDRNet, a <i>Multi-Objective Fake Data Regression Network</i> model that integrates the loss function and multiple metrics strategies. The key idea is to deploy a malicious attack model on the server with the purpose of generating fake data and labels and continuously approximating the shared gradients between clients and the server, thereby recovering clients' private data. Experimental results demonstrate that the MOFDRNet model has significant advantages in implementing data leakage attacks. Finally, we also discuss the differential privacy defense approach in this study.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 9-11","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143809385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hierarchical Feature Selection Based on Instance Correlation and Label Semantic Structure","authors":"Yu Mao,&nbsp;Chunyu Shi,&nbsp;Zhiyi Cai,&nbsp;Hui Chen,&nbsp;Lei Guo","doi":"10.1002/cpe.70079","DOIUrl":"https://doi.org/10.1002/cpe.70079","url":null,"abstract":"<div>\u0000 \u0000 <p>Hierarchical classification learning aims to exploit the hierarchical relationship between data categories. Making full use of the hierarchical structure between class labels can effectively reduce the number of categories for each classification task and improve the accuracy of classification. For hierarchical feature selection, usually the more similar two labels are, the more features they share. However, existing hierarchical feature selection algorithms often ignore this. In addition, current hierarchical feature selection algorithms do not deeply consider the semantic structure between labels when exploiting label correlations. In this article, we propose a hierarchical feature selection based on instance correlation and label semantic structure. This algorithm expresses the correlation between instances with the help of Laplacian matrix. Then, the instance correlation is combined with the semantic relationship between labels in the hierarchical structure to construct a hierarchical feature selection model. To prove the effectiveness of the proposed algorithm, a large number of experiments are conducted on hierarchical datasets in different fields, and multiple hierarchical feature selection are compared. The experimental results demonstrate that the proposed algorithm has significant performance superiority.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 9-11","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143809820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DARB: A Dynamic Architecture for Data Replica Balancing","authors":"Rhauani Weber Aita Fazul,&nbsp;Odorico Machado Mendizabal,&nbsp;Patrícia Pitthan Barcelos","doi":"10.1002/cpe.70050","DOIUrl":"https://doi.org/10.1002/cpe.70050","url":null,"abstract":"<div>\u0000 \u0000 <p>Distributed file systems, such as HDFS, are designed to support applications that handle large volumes of data. Data replication, which is at the core of the HDFS storage model, is essential for fault tolerance and performance. As new data are loaded into the system, the distribution of data blocks replicated among the nodes may become dissimilar affecting replica balancing and data locality. The HDFS Balancer is the official solution for redistributing the data already stored in the cluster. However, it overlooks the specific needs of the applications during data rearrangement and requires manual intervention by system administrators—a dependency that is often inadequate and inefficient. To address these limitations, this work presents DARB, a Dynamic Architecture for Replica Balancing that combines reactive and proactive strategies. The former uses the Prioritized Replica Balancing Policy to customize the replica balancing through configurable priorities. The latter consists of an event-driven strategy that makes the overall balancing process in HDFS transparent. DARB comprises modular components and a metrics observation model that identifies and determines when corrective actions should be taken. It also automatically triggers the HDFS Balancer based on standardized trigger events. The evaluation results reinforce that the proposed solution removes the need for manual configuration and execution while actively acting to keep the cluster balanced, taking into account performance, reliability, and data availability perspectives. Thus, DARB offers a sophisticated and specialized balancing solution that makes the balancing process seamless and flexible, introducing to the HDFS the concept of context-aware replica balancing.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 9-11","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143793415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Modified Jellyfish Search Algorithm for Task Scheduling in Fog-Cloud Systems","authors":"Nupur Jangu,&nbsp;Zahid Raza","doi":"10.1002/cpe.70054","DOIUrl":"https://doi.org/10.1002/cpe.70054","url":null,"abstract":"<div>\u0000 \u0000 <p>Integration of fog and cloud has become increasingly important in the age of IoT, where everything is connected to the Internet. The cloud-only models face many challenges when serving the requests from IoT devices due to several factors such as latency, network congestion, data privacy, and security. Despite the popularity and numerous advantages of hybrid models, task scheduling is still an unsolvable multiobjective optimization problem. This research uses an improved bioinspired jellyfish search algorithm to solve the nonlinear np-hard task scheduling optimization problem. The work proposes a multiobjective improved jellyfish search (MOIJS) framework using a multiobjective adaptation function to minimize the make-span, cost, and power consumption that benefit customers and providers by considering the expenses associated with execution and power consumption. The performance of MOIJS is evaluated by comparing it with the discrete nondominated sorting genetic algorithm II using a MATLAB simulator. The experimental outcomes demonstrate the proposed work's efficacy in reducing the make-span, cost, and energy in cloud-fog environments in different batches of tasks.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 9-11","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143793417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unblocking Placement and Routing in Rearrangeable Multi-Stage Networks","authors":"Caio Von Rondow Morais,&nbsp;Jeronimo Penha,&nbsp;José Augusto M. Nacif,&nbsp;Ricardo S. Ferreira","doi":"10.1002/cpe.70055","DOIUrl":"https://doi.org/10.1002/cpe.70055","url":null,"abstract":"<div>\u0000 \u0000 <p>High-performance computing demands efficient and scalable interconnections. Although crossbar networks offer high parallel bandwidth, their <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>O</mi>\u0000 <mo>(</mo>\u0000 <msup>\u0000 <mrow>\u0000 <mi>n</mi>\u0000 </mrow>\u0000 <mrow>\u0000 <mn>2</mn>\u0000 </mrow>\u0000 </msup>\u0000 <mo>)</mo>\u0000 </mrow>\u0000 <annotation>$$ Oleft({n}^2right) $$</annotation>\u0000 </semantics></math> costs are prohibitively expensive. Multi-stage networks provide scalability with <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>O</mi>\u0000 <mo>(</mo>\u0000 <mi>n</mi>\u0000 <mi>log</mi>\u0000 <mi>n</mi>\u0000 <mo>)</mo>\u0000 </mrow>\u0000 <annotation>$$ Oleft(nlog nright) $$</annotation>\u0000 </semantics></math> cost, yet they may block certain routing patterns. Rearrangeable multistage networks (RMNs) have emerged as a cost-effective solution, enabling internal connection rearrangements to make all paths accessible without network blocking. However, discovering optimal rearrangement strategies remains a challenge for unblocking large-scale (256 connections) reconfigurable networks. We advance the state of the art by effectively managing workloads with over 50% without blocking. When nearly all connections are required, we introduce routing strategies to rearrange existing connections. In the presence of multicast, where the configuration space exceeds <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mn>1</mn>\u0000 <msup>\u0000 <mrow>\u0000 <mn>0</mn>\u0000 </mrow>\u0000 <mrow>\u0000 <mn>671</mn>\u0000 </mrow>\u0000 </msup>\u0000 </mrow>\u0000 <annotation>$$ 1{0}^{671} $$</annotation>\u0000 </semantics></math>, we propose novel strategies employing simulated annealing for placement and Monte Carlo tree search for routing to prioritize multicast connections, which simultaneously maximize the number of connections by minimizing conflicts and reducing the number of extra stages. To the best of our knowledge, we first demonstrate that the Benes network is not rearrangeable under multicast conditions. We propose exploring the rearrangeability of shuffle exchanges with additional network stages.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 9-11","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143793424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Modified Deep Learning Model in Proactive Decision-Making for Handover Management in 5G","authors":"G. Arul Dalton,&nbsp;A. Bamila Virgin Louis,&nbsp;A. Ramachandran,&nbsp;J. Savija","doi":"10.1002/cpe.70023","DOIUrl":"https://doi.org/10.1002/cpe.70023","url":null,"abstract":"<div>\u0000 \u0000 <p>With the fast expansion of mobile devices and internet traffic, it is becoming critical to deliver dependable and robust services. HetNets and large networks are highlighted as probable solutions to the nearing capacity obstructions; however, they also present substantial challenges in terms of handover (HO) management. In cellular telecommunications, HO describes the procedure of moving an active call or data link from one base station (BS) to another. Whenever a mobile phone switches to another cell while a conversation is in progress, the MSC (mobile switching center) shifts the call to an alternate channel assigned to the new BS. The major objective of this work is to assist in how the HCP includes the functions of the 5G network, in which a modified deep learning architecture is introduced for predicting the NDR (network download rate) efficiently. In particular, a modified DNN architecture is introduced for this purpose. As a result, the proposed model attained a lower HO delay of 10.207 ms at a speed of 60 m/s, which surpasses the results of established techniques. From the analysis, it is proven that the proposed work efficiently increases the performance of the network without any interruption during transitions among cells.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 9-11","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143793419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CGKDFL: A Federated Learning Approach Based on Client Clustering and Generator-Based Knowledge Distillation for Heterogeneous Data","authors":"Sanfeng Zhang,&nbsp;Hongzhen Xu,&nbsp;Xiaojun Yu","doi":"10.1002/cpe.70048","DOIUrl":"https://doi.org/10.1002/cpe.70048","url":null,"abstract":"<div>\u0000 \u0000 <p>In practical, real-world complex networks, data distribution is frequently decentralized and Non-Independently Identically Distributed (Non-IID). This heterogeneous data presents a significant challenge for federated learning. Such problems include the generation of biased global models, the lack of sufficient personalization capability of local models, and the difficulty in absorbing global knowledge. We propose a Federated Learning Approach Based on Client Clustering and Generator-based Knowledge Distillation(CGKDFL) for heterogeneous data. Firstly, to reduce the global model bias, we propose a clustering federated learning approach that only requires each client to transmit some of the parameters of the selected layer, thus reducing the number of parameters. Subsequently, to circumvent the absence of global knowledge resulting from clustering, a generator designed to improve privacy features and increase diversity is developed on the server side. This generator produces feature representation data that aligns with the specific tasks of the client by utilizing the labeling information provided by the client. This is achieved without the need for any external dataset. The generator then transfers its global knowledge to the local model. The client can then utilize this information for knowledge distillation. Finally, extensive experiments were conducted on three heterogeneous datasets. The results demonstrate that CGKDFL outperforms the baseline method by a minimum of <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mn>7</mn>\u0000 <mo>.</mo>\u0000 <mn>24</mn>\u0000 <mo>%</mo>\u0000 </mrow>\u0000 <annotation>$$ 7.24% $$</annotation>\u0000 </semantics></math>, <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mn>6</mn>\u0000 <mo>.</mo>\u0000 <mn>73</mn>\u0000 <mo>%</mo>\u0000 </mrow>\u0000 <annotation>$$ 6.73% $$</annotation>\u0000 </semantics></math>, and <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mn>3</mn>\u0000 <mo>.</mo>\u0000 <mn>13</mn>\u0000 <mo>%</mo>\u0000 </mrow>\u0000 <annotation>$$ 3.13% $$</annotation>\u0000 </semantics></math> regarding accuracy on the three heterogeneous datasets. Additionally, it outperforms the compared methods regarding convergence speed in all cases.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 9-11","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143793423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Structure-Aware Representation Learning for Effective Performance Prediction","authors":"Tarek Ramadan,&nbsp;Nathan Pinnow,&nbsp;Chase Phelps,&nbsp;Jayaraman J. Thiagarajan,&nbsp;Tanzima Z. Islam","doi":"10.1002/cpe.70046","DOIUrl":"https://doi.org/10.1002/cpe.70046","url":null,"abstract":"<p>Application performance is a function of several unknowns stemming from the interactions between the application, runtime, OS, and underlying hardware, making it challenging to model performance using deep learning techniques, especially without a large labeled dataset. Collecting such labeled longitudinal datasets can take weeks. Intuitively, developers could save analysis time during code development by taking a comparative approach between multiple applications. However, the unknown dynamic interactions between applications and execution environments make it difficult for deep learning-based models to predict the performance of new applications. In this paper, we address these problems by presenting a labeled dataset for the community and taking a comparative analysis approach to explore the source code differences between different correct implementations of the same problem. This paper assesses the feasibility of using purely static information, for example, Abstract Syntax Tree (AST), of applications to predict performance change based on code structure. We evaluate several deep learning-based representation learning techniques for source code and propose an architecture for the tree-based Long Short-Term Memory (LSTM) models to discover latent representations for a source code's hierarchical structure. We demonstrate that our proposed architecture enables feed-forward predictive models to predict change in performance using source code with up to 84% accuracy.</p>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 9-11","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/cpe.70046","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143793525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Distributed Parallel Network Intrusion Detection System Based on Ray Framework With GPU Acceleration","authors":"Wenbin Yao,&nbsp;Longcan Hu,&nbsp;Yingying Hou","doi":"10.1002/cpe.70021","DOIUrl":"https://doi.org/10.1002/cpe.70021","url":null,"abstract":"<div>\u0000 \u0000 <p>In the era of the Internet of Things and big data, the training of machine learning models has become increasingly demanding due to the vast amounts of data involved. Reducing training time and improving classification accuracy are essential. This article proposes a high-performance attack detection model (AE-XGBoost) based on the distributed data parallel processing framework-Ray. First, a solution called Dynamic Resource Adjustment for Model Training enhances training speed by dynamically adjusting resources, preventing resource idleness or overload, and ensuring optimal resource utilization at each stage. Second, the Dual-Link Loss Autoencoder algorithm is employed for feature mining, improving anomaly detection and enabling clear visualization of normal and anomalous data. Finally, the data parallel XGBoost method is applied for attack classification. Experimental results on five public large-scale datasets demonstrate that the proposed model outperforms several well-established benchmark classification models in both performance and accuracy.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 9-11","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143793418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Multi-Scenario Multi-Period Facility Location-Allocation Model and Algorithm for Pre-Disaster Planning","authors":"Le Xu,&nbsp;Yong Xu","doi":"10.1002/cpe.70052","DOIUrl":"https://doi.org/10.1002/cpe.70052","url":null,"abstract":"<div>\u0000 \u0000 <p>Due to the diversity, periodicity, and complexity of disasters, government agencies and humanitarian organizations must engage in comprehensive pre-disaster planning. The facility location and emergency material allocation are particularly critical components with this planning process. Therefore, this paper designs a multi-scenario multi-period facility location-allocation model (MSMPFLA) for pre-disaster planning. The model also focuses on the diversity and periodicity characteristics of disasters by constructing various disaster scenarios to simulate emergency material allocation schemes in different rescue periods. To address this model, we propose a hybrid discrete crow search algorithm and material allocation algorithm (DCSA-MA). Experimental results indicate that the DCSA-MA significantly outperforms other algorithms in terms of solution quality, convergence rate, computation time, and stability. Through the Wilcoxon rank sum test, the DCSA-MA demonstrates superior optimization performance in majority of disaster scenarios. Consequently, DCSA-MA is an effective and stable method for solving the MSMPFLA problem. In comparison to traditional model, the MSMPFLA model offers more stable and feasible solutions, thereby validating its practicality and applicability in real-world scenarios. In addition, the impacts of penalty cost and the number of open facility on the MSMPFLA model are assessed in a series of sensitivity analyses, so as to inform decision-makers to a develop reliable emergency material allocation scheme.</p>\u0000 </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 9-11","pages":""},"PeriodicalIF":1.5,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143793416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}