Future Generation Computer Systems-The International Journal of Escience最新文献_第3页

High performance graph-parallel accelerator design 高性能图形并行加速器设计

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2026-07-01 Epub Date: 2026-01-23 DOI: 10.1016/j.future.2026.108385

Cemil Kaan Akyol , Muhammet Mustafa Ozdal , Ozcan Ozturk

{"title":"High performance graph-parallel accelerator design","authors":"Cemil Kaan Akyol , Muhammet Mustafa Ozdal , Ozcan Ozturk","doi":"10.1016/j.future.2026.108385","DOIUrl":"10.1016/j.future.2026.108385","url":null,"abstract":"<div><div>Graph applications are becoming increasingly important with their widespread usage and the amounts of data they deal with. Biological and social web graphs are well-known examples that show the importance of efficiently processing graph analytic applications and problems. Due to limited resources, efficiency and performance are much more critical in embedded systems. We propose an efficient source-to-source-based methodology for graph applications that gives the freedom of not knowing the low-level details of parallelization and distribution by translating any vertex-centric C++ graph application into a pipelined SystemC model. High-Level Synthesis (HLS) tools can synthesize the generated SystemC model to obtain the design of the hardware. To support different types of graph applications, we have implemented features like non-standard application support, active set functionality, asynchronous execution support, conditional pipeline support, non-neighbor data access support, multiple pipeline support, and user-defined data type functionality. Our accelerator development flow can generate better-performing accelerators than OpenCL. Furthermore, it dramatically reduces the design time compared to using HLS tools. Therefore, the proposed methodology can generate fast accelerators with minimal effort using a high-level language description from the user.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"180 ","pages":"Article 108385"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146033295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

RoWD: Automated rogue workload detector for HPC security RoWD：用于高性能计算安全的自动流氓工作负载检测器

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2026-07-01 Epub Date: 2026-01-22 DOI: 10.1016/j.future.2026.108392

Francesco Antici , Jens Domke , Andrea Bartolini , Zeynep Kiziltan , Satoshi Matsuoka

{"title":"RoWD: Automated rogue workload detector for HPC security","authors":"Francesco Antici , Jens Domke , Andrea Bartolini , Zeynep Kiziltan , Satoshi Matsuoka","doi":"10.1016/j.future.2026.108392","DOIUrl":"10.1016/j.future.2026.108392","url":null,"abstract":"<div><div>The increasing reliance on High-Performance Computing (HPC) systems to execute complex scientific and industrial workloads raises significant security concerns related to the misuse of HPC resources for unauthorized or malicious activities. Rogue job executions can threaten the integrity, confidentiality, and availability of HPC infrastructures. Given the scale and heterogeneity of HPC job submissions, manual or ad hoc monitoring is inadequate to effectively detect such misuse. Therefore, automated solutions capable of systematically analyzing job submissions are essential to detect rogue workloads. To address this challenge, we present RoWD (Rogue Workload Detector), the first framework for automated and systematic security screening of the HPC job-submission pipeline. RoWD is composed of modular plug-ins that classify different types of workloads and enable the detection of rogue jobs through the analysis of job scripts and associated metadata. We deploy RoWD on the Supercomputer Fugaku to classify AI workloads and release SCRIPT-AI, the first dataset of annotated job scripts labeled with workload characteristics. We evaluate RoWD on approximately 50K previously unseen jobs executed on Fugaku between 2021 and 2025. Our results show that RoWD accurately classifies AI jobs (achieving an F1 score of 95%), is robust against adversarial behavior, and incurs low runtime overhead, making it suitable for strengthening the security of HPC environments and for real-time deployment in production systems.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"180 ","pages":"Article 108392"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146033300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Vertical auto-scaling mechanism for elastic memory management of containerized applications in Kubernetes Kubernetes中容器化应用弹性内存管理的垂直自动扩展机制

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2026-07-01 Epub Date: 2026-01-22 DOI: 10.1016/j.future.2026.108407

Taeshin Kang, Minwoo Kang, Heonchang Yu

{"title":"Vertical auto-scaling mechanism for elastic memory management of containerized applications in Kubernetes","authors":"Taeshin Kang, Minwoo Kang, Heonchang Yu","doi":"10.1016/j.future.2026.108407","DOIUrl":"10.1016/j.future.2026.108407","url":null,"abstract":"<div><div>Cloud service providers typically offer containers with fixed resource sizes. However, cloud users often overprovision container resources to prevent service interruptions caused by resource shortages. This practice leads to low utilization of system resources in the cloud. To address this issue, cloud service providers offer container auto-scaling. They primarily support horizontal auto-scaling, which provides horizontal elasticity. However, this approach has limitations in responding promptly to unexpected spikes in resource usage and in optimizing resource utilization. Vertical auto-scaling can help overcome these limitations. Its importance is increasing, particularly for stateful and real-time applications that require immediate resource elasticity. Nevertheless, vertical elasticity remains difficult to achieve and has not been actively researched or widely implemented. This study proposes a vertical auto-scaling mechanism for elastic memory management in container-based applications running in Kubernetes, which is widely recognized as the standard platform for container orchestration. In the proposed approach, high-priority tasks are given priority for scaling up, while tasks that cannot undergo scale-up are suspended using the <em>cgroup freeze</em> feature to prevent further memory allocation. If memory pressure persists and task termination becomes unavoidable, tasks are terminated in ascending order of priority, starting with the lowest. Once memory pressure is relieved, stateful applications are restarted from the point at which they were suspended. Compared to the default Kubernetes environment without vertical elasticity, EVMMv2 reduced the total execution time of stateful applications by up to 40% and improved the request success rate of stateless applications by 37%.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"180 ","pages":"Article 108407"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146033299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

FedAPE: Heterogeneous federated learning with attention-guided aggregation and prototype enhancement 基于注意引导聚合和原型增强的异质联邦学习

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2026-07-01 Epub Date: 2026-02-06 DOI: 10.1016/j.future.2026.108417

Xiao Wang , Zhengda Wu , Jinghua Zhu

{"title":"FedAPE: Heterogeneous federated learning with attention-guided aggregation and prototype enhancement","authors":"Xiao Wang , Zhengda Wu , Jinghua Zhu","doi":"10.1016/j.future.2026.108417","DOIUrl":"10.1016/j.future.2026.108417","url":null,"abstract":"<div><div>Prototype-based heterogeneous federated learning has emerged as an efficient paradigm that reduces communication overhead through prototype transmission while preserving client privacy. However, current approaches suffer from three critical limitations: 1) conventional prototype averaging overlooks intra-class variations; 2) sensitivity to imbalanced class distributions in client feature spaces; and 3) restricted generalization capacity in heterogeneous environments. This paper presents FedAPE - a novel Attention-guided aggregation and Prototype Enhancement framework for heterogeneous federated learning. Our technical contributions are threefold: First, we develop an attention-based feature aggregation mechanism that dynamically captures intra-class similarity patterns to learn discriminative class-specific prototypes. Second, we introduce a contrastive learning objective that explicitly enforces inter-class separability and intra-class compactness during local training. Third, we devise an adaptive prototype enhancement strategy that synthesizes representative pseudo-prototypes in under-represented regions of the feature space, effectively compensating for class distribution imbalance. Comprehensive evaluations on CIFAR-10, CIFAR-100, and GTSRB datasets demonstrate FedAPE’s superiority over state-of-the-art methods, achieving accuracy improvements of 2.82%, 5.65%, and 2.94%, respectively, in heterogeneous model configurations. The results validate our framework’s enhanced capability in handling both feature heterogeneity and class imbalance scenarios.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"180 ","pages":"Article 108417"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146134533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MoFormer: A centrality-aware multi-task graph transformer with multi-gate mixture-of-experts for link-level network performance modeling MoFormer：用于链路级网络性能建模的具有多门混合专家的中心性感知多任务图转换器

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2026-07-01 Epub Date: 2026-01-24 DOI: 10.1016/j.future.2026.108406

Hanlin Liu , Aliya Bao , Mingyue Li , Yintan Ai , Hua Li

{"title":"MoFormer: A centrality-aware multi-task graph transformer with multi-gate mixture-of-experts for link-level network performance modeling","authors":"Hanlin Liu , Aliya Bao , Mingyue Li , Yintan Ai , Hua Li","doi":"10.1016/j.future.2026.108406","DOIUrl":"10.1016/j.future.2026.108406","url":null,"abstract":"<div><div>Link-level network performance modeling (NPM) facilitates efficient traffic control, precise fault localization, and reliable resource management in emerging network paradigms such as Software-Defined Networking and Intent-Based Networking. A variety of models, such as Long Short-Term Memory and Graph Neural Networks (GNNs), are utilized to enhance the effectiveness of NPM. However, a practical NPM requires the generalization ability to adapt to diverse network topologies and prediction tasks without retraining. To meet this requirement, graph Transformer models are a breakthrough by encoding nodes and their structural features into tokens, breaking free from the dependencies on fixed graph structures typical of traditional GNNs. Nevertheless, they mostly focus on node-centric representations, which are insufficient to capture the fine-grained interactions and dependencies between links, thus limiting their applicability in link-level NPM. In this paper, we propose a centrality-aware multi-task graph Transformer with multi-gate mixture-of-experts (MMoE), named MoFormer, for link-level NPM. Specifically, a link-centric tokenized graph representation method is proposed to transform each link and its neighborhood information into a sequence of tokens guided by the routing protocol. A routing-aware betweenness centrality encoding mechanism is further developed to enhance the ability to characterize the tokens considering the relative importance of each link. MoFormer takes advantage of MMoE combined with Transformer to enable joint learning of multiple prediction tasks. Experimental results on both simulated and real-world datasets demonstrate the significant improvements of MoFormer over existing state-of-the-art baselines while maintaining superior generalization ability.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"180 ","pages":"Article 108406"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146047990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A reliability- and latency-driven task allocation framework for workflow applications in the edge-hub-cloud continuum 一个可靠性和延迟驱动的任务分配框架，用于边缘中心云连续体中的工作流应用程序

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2026-07-01 Epub Date: 2026-02-03 DOI: 10.1016/j.future.2026.108414

Andreas Kouloumpris , Georgios L. Stavrinides , Maria K. Michael , Theocharis Theocharides

{"title":"A reliability- and latency-driven task allocation framework for workflow applications in the edge-hub-cloud continuum","authors":"Andreas Kouloumpris , Georgios L. Stavrinides , Maria K. Michael , Theocharis Theocharides","doi":"10.1016/j.future.2026.108414","DOIUrl":"10.1016/j.future.2026.108414","url":null,"abstract":"<div><div>A growing number of critical workflow applications leverage a streamlined edge-hub-cloud architecture, which diverges from the conventional edge computing paradigm. An edge device, in collaboration with a hub device and a cloud server, often suffices for their reliable and efficient execution. However, task allocation in this streamlined architecture is challenging due to device limitations and diverse operating conditions. Given the inherent criticality of such workflow applications, where reliability and latency are vital yet conflicting objectives, an exact task allocation approach is typically required to ensure optimal solutions. As no existing method holistically addresses these issues, we propose an exact multi-objective task allocation framework to jointly optimize the overall reliability and latency of a workflow application in the specific edge-hub-cloud architecture. We present a comprehensive binary integer linear programming formulation that considers the relative importance of each objective. It incorporates time redundancy techniques, while accounting for crucial constraints often overlooked in related studies. We evaluate our approach using a relevant real-world workflow application, as well as synthetic workflows varying in structure, size, and criticality. In the real-world application, our method achieved average improvements of 84.19% in reliability and 49.81% in latency over baseline strategies, across relevant objective trade-offs. Overall, the experimental results demonstrate the effectiveness and scalability of our approach across diverse workflow applications for the considered system architecture, highlighting its practicality with runtimes averaging between 0.03 and 50.94 seconds across all examined workflows.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"180 ","pages":"Article 108414"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146110188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

GraalDoss: Direct object snapshotting and sharing for cloud-native applications GraalDoss：云原生应用程序的直接对象快照和共享

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2026-07-01 Epub Date: 2026-01-20 DOI: 10.1016/j.future.2026.108375

Ivan Ristović , Vojin Jovanović , Peter Hofer , Milena Vujošević Janičić

{"title":"GraalDoss: Direct object snapshotting and sharing for cloud-native applications","authors":"Ivan Ristović , Vojin Jovanović , Peter Hofer , Milena Vujošević Janičić","doi":"10.1016/j.future.2026.108375","DOIUrl":"10.1016/j.future.2026.108375","url":null,"abstract":"<div><div>Modern cloud-computing providers operate on a pay-as-you-use billing model, with computing power and memory being the most important and expensive resources. Due to resource costs, cloud-native applications should start fast while minimizing startup time and memory footprint over multiple application instances. However, modern workloads consist of large amounts of data, often requiring initialization which introduces repeated CPU work across application instances. Current cloud-native solutions that pre-initialize application code and data operate at application-build time to enable sharing during execution. However, these solutions do not consider data that becomes available or can only be initialized during application execution.</div><div>We present <span>Doss</span>, a direct object snapshotting and sharing mechanism for cloud-native applications. <span>Doss</span> snapshots the state of the object graph directly from the executing language-runtime heap. This allows <span>Doss</span> to achieve constant deserialization overhead with memory mappings. <span>Doss</span> shares warmed-up data snapshots across compatible language-runtime instances, reducing the memory overhead of the system, and avoiding cold starts. We implement Graal<span>Doss</span> in Java as part of GraalVM. Graal<span>Doss</span> maintains a constant data-cache memory overhead across multiple application instances, eliminating costly data initialization. In microservice applications, Graal<span>Doss</span> reduces the total memory footprint by 44% for 8 microservice instances and improves first-response times by 51%. In natural language processing applications, Graal<span>Doss</span> improves total execution times by several orders of magnitude.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"180 ","pages":"Article 108375"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146014881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SeHP-CSQ: A secure, high-performance cross-shard queuing model SeHP-CSQ：一个安全、高性能的跨分片队列模型

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2026-07-01 Epub Date: 2026-01-20 DOI: 10.1016/j.future.2026.108376

Hui Dai , Lingyun Yuan , Haochen Bao , Han Chen

{"title":"SeHP-CSQ: A secure, high-performance cross-shard queuing model","authors":"Hui Dai , Lingyun Yuan , Haochen Bao , Han Chen","doi":"10.1016/j.future.2026.108376","DOIUrl":"10.1016/j.future.2026.108376","url":null,"abstract":"<div><div>Blockchain sharding parallelises processing to boost throughput. Cross-shard transactions’ low transmission efficiency and security risks limit system scalability. We propose a secure cross-shard high-performance processing queuing model. First, we model hybrid multi-distribution batch arrival-processing and accurately depict transaction arrival and processing dynamics. Second, we construct a cross-shard transaction processing queuing model based on M/M/1/N queuing, along with a metric system for key performance indicators. Modifying the queue capacity to regulate batch control of cross-shard transactions directed at the target shard, thereby improving robustness and scalability. Third, we design a dynamic adaptive malicious transaction analysis bound, which derives an upper bound on the real-time tail probability via Chernoff’s inequality and Hoeffding’s inequality, and prove that the analysis bound can converge at an exponential rate under any shard size, thus effectively limiting the impact of malicious behaviours on the security of the shard system. Experimental results show that the proposed queuing model can reach a maximum throughput of about 8.0 × 10<sup>4</sup> TPS and achieve load balancing in high concurrency scenarios. The queuing waiting time is less than 0.5 ms, with the overload probability and the system failure probability converging to 0%, which verifies that the model has adequate security While ensuring high processing efficiency.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"180 ","pages":"Article 108376"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146014877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

PSCD : A privacy-preserving framework for structural constraint mitigation in deep neural networks on encrypted distributed datasets PSCD：加密分布式数据集上深度神经网络结构约束缓解的隐私保护框架

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2026-07-01 Epub Date: 2026-01-20 DOI: 10.1016/j.future.2026.108390

Yuhao Zhang , Weiwei Zhao , Changhui Hu

{"title":"PSCD : A privacy-preserving framework for structural constraint mitigation in deep neural networks on encrypted distributed datasets","authors":"Yuhao Zhang , Weiwei Zhao , Changhui Hu","doi":"10.1016/j.future.2026.108390","DOIUrl":"10.1016/j.future.2026.108390","url":null,"abstract":"<div><div>The proliferation of deep neural networks (DNNs) drives the need for collaborative data processing across distributed nodes in next-generation systems. This mode poses a potential threat to distributed data privacy, necessitating the development of more reliable privacy-preserving machine learning (PPML) solutions. The functional encryption (FE) provides a new paradigm for PPML due to its unique advantages. Unfortunately, privacy requirements in existing FE-based schemes impose a priori constraints on permissible neural architectures, highlighting a fundamental tension with model expressiveness. To close this gap, we design a privacy-preserving DNN framework (PSCD) based on FE, mitigating structural constraints on model by integrating three independent modules. Specifically, we first design a secure aggregation module SAM with FE to ensure the confidentiality of local data upload. Then, we introduce FM Sketch to propose a query control module QCM to control the number of times ciphertext vectors are queried by cloud server. Finally, we develop a privacy-preserving training mechanism PPTM, which incorporates Dropout to flexibly adjust the network structure and synchronously enhance the robustness of model. Formal security analysis proves that PSCD can against semi-honest attacks and collusion attacks. Experiments on real-world datasets demonstrate that PSCD achieves at least a 48.5% improvement in operational efficiency and a 38.9% reduction in communication overhead compared to benchmark PPML schemes, while maintaining model accuracy comparable to that of a plaintext DNN.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"180 ","pages":"Article 108390"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146014915","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Knowledge distillation-based Multi-Optimization intrusion detection system 基于知识提取的多优化入侵检测系统

IF 6.2 2区计算机科学

Future Generation Computer Systems-The International Journal of Escience Pub Date : 2026-07-01 Epub Date: 2025-12-31 DOI: 10.1016/j.future.2025.108296

Haofan Wang , Farah Kandah

{"title":"Knowledge distillation-based Multi-Optimization intrusion detection system","authors":"Haofan Wang , Farah Kandah","doi":"10.1016/j.future.2025.108296","DOIUrl":"10.1016/j.future.2025.108296","url":null,"abstract":"<div><div>Network attacks have expanded in scope, increased in frequency, and evolved in many ways in recent years. Internet of Things (IoT) devices, due to their limited computational resources, massive deployment, direct exposure to the public Internet, and lack of maintenance, face even more severe threat landscapes. Nowadays, numerous lightweight methods have been proposed, but they all rely on single-perspective optimizations, making it difficult to achieve an optimal balance between performance and computational resource consumption. In this work, we proposed a Knowledge Distillation-based Multi-Optimization Intrusion Detection System (KDMO-IDS) that reduces resource consumption at the feature, sample, and model levels. At the feature level, we compute the Analysis of Variance (ANOVA) F-value for each feature to rank them and determine the optimal subset. At the sample level, we use MiniBatchKMeans with Medoid clustering to compress data under preset ratios At the model level, we combine knowledge distillation with attention transfer so that a compact student model retains the performance of its teacher, further optimized by block operator fusion, pruning, and early stopping. We conduct extensive ablation studies to validate the contribution of each component. Experiments on WUSTL-IIoT and X-IIoTID datasets show that our proposed KDMO-IDS demonstrates superior performance and exhibits strong lightweight characteristics and generalizability compare to existing baseline models, making it well-suited for seamless integration into edge-cloud and distributed computing environments and providing a scalable security solution for next-generation high-performance IoT systems.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"180 ","pages":"Article 108296"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145893754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0