Pub Date : 2024-08-06DOI: 10.1007/s00607-024-01329-3
Jiahao Li, Tianhan Gao, Qingwei Mi
Reinforcement learning algorithms show significant variations in performance across different environments. Optimization for reinforcement learning thus becomes the major research task since the instability and unpredictability of the reinforcement learning algorithms have consistently hindered their generalization capabilities. In this study, we address this issue by optimizing the algorithm itself rather than environment-specific optimizations. We start by tackling the uncertainty caused by the mutual influence of original action interferences, aiming to enhance the overall performance. The Phasic Parallel-Network Policy (PPP), which is a deep reinforcement learning framework. It diverges from the traditional policy actor-critic method by grouping the action space based on action correlations. The PPP incorporates parallel network structures and combines network optimization strategies. With the assistance of the value network, the training process is divided into different specific stages, namely the Extra-group Policy Phase and the Inter-group Optimization Phase. PPP breaks through the traditional unit learning structure. The experimental results indicate that it not only optimizes training effectiveness but also reduces training steps, enhances sample efficiency, and significantly improves stability and generalization.
{"title":"Phasic parallel-network policy: a deep reinforcement learning framework based on action correlation","authors":"Jiahao Li, Tianhan Gao, Qingwei Mi","doi":"10.1007/s00607-024-01329-3","DOIUrl":"https://doi.org/10.1007/s00607-024-01329-3","url":null,"abstract":"<p>Reinforcement learning algorithms show significant variations in performance across different environments. Optimization for reinforcement learning thus becomes the major research task since the instability and unpredictability of the reinforcement learning algorithms have consistently hindered their generalization capabilities. In this study, we address this issue by optimizing the algorithm itself rather than environment-specific optimizations. We start by tackling the uncertainty caused by the mutual influence of original action interferences, aiming to enhance the overall performance. The <i>Phasic Parallel-Network Policy</i> (PPP), which is a deep reinforcement learning framework. It diverges from the traditional policy actor-critic method by grouping the action space based on action correlations. The PPP incorporates parallel network structures and combines network optimization strategies. With the assistance of the value network, the training process is divided into different specific stages, namely the Extra-group Policy Phase and the Inter-group Optimization Phase. PPP breaks through the traditional unit learning structure. The experimental results indicate that it not only optimizes training effectiveness but also reduces training steps, enhances sample efficiency, and significantly improves stability and generalization.</p>","PeriodicalId":10718,"journal":{"name":"Computing","volume":null,"pages":null},"PeriodicalIF":3.7,"publicationDate":"2024-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141931602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-31DOI: 10.1007/s00607-024-01322-w
Gyan Singh, Amit K. Chaturvedi
Recent years have seen an exponential rise in data produced by Internet of Things (IoT) applications. Cloud servers were not designed for such extensive data, leading to challenges like increased makespan, cost, bandwidth, energy consumption, and network latency. To address these, the cloud–fog environment has emerged as an extension to cloud servers, offering services closer to IoT devices. Scheduling workflow applications to optimize multiple conflicting objectives in cloud fog is an NP-hard problem. Particle Swarm Optimization (PSO) is a good choice for multi-objective solutions due to its simplicity and rapid convergence. However, it has shortcomings like premature convergence and stagnation. To address these challenges, we formalize a theoretical background for scheduling workflow applications in the cloud–fog environment with multiple conflicting objectives. Subsequently, we propose an adaptive particle swarm optimization (APSO) algorithm with novel enhancements, including an S-shaped sigmoid function to dynamically decrease inertia weight and a linear updating mechanism for cognitive factors. Their integration in cloud–fog environments has not been previously explored. This novel application addresses unique challenges of workflow scheduling in cloud–fog systems, such as heterogeneous resource management, energy consumption, and increased cost. The effectiveness of APSO is evaluated using a real-world scientific workflow in a simulated cloud–fog environment and compared with four meta-heuristics. Our proposed workflow scheduling significantly reduces makespan and energy consumption without compromising overall cost compared to other meta-heuristics.
近年来,物联网(IoT)应用产生的数据呈指数级增长。云服务器并不是为处理如此大量的数据而设计的,这导致了诸如时间跨度、成本、带宽、能耗和网络延迟增加等挑战。为了解决这些问题,云雾环境作为云服务器的扩展而出现,提供更接近物联网设备的服务。在云雾环境中调度工作流应用程序以优化多个相互冲突的目标是一个 NP 难问题。粒子群优化(PSO)因其简单性和快速收敛性,是多目标解决方案的不错选择。然而,它也存在过早收敛和停滞等缺点。为了应对这些挑战,我们正式提出了在云雾环境中调度具有多个冲突目标的工作流应用的理论背景。随后,我们提出了一种自适应粒子群优化(APSO)算法,并对该算法进行了新的改进,包括使用 S 型 sigmoid 函数动态降低惯性权重和认知因素的线性更新机制。在云雾环境中整合这些算法,此前还从未有过探索。这种新颖的应用解决了云雾系统中工作流调度所面临的独特挑战,如异构资源管理、能源消耗和成本增加等。我们使用模拟云雾环境中的真实科学工作流对 APSO 的有效性进行了评估,并与四种元启发式算法进行了比较。与其他元启发式相比,我们提出的工作流调度方法在不影响总体成本的情况下显著降低了时间跨度和能耗。
{"title":"A cost, time, energy-aware workflow scheduling using adaptive PSO algorithm in a cloud–fog environment","authors":"Gyan Singh, Amit K. Chaturvedi","doi":"10.1007/s00607-024-01322-w","DOIUrl":"https://doi.org/10.1007/s00607-024-01322-w","url":null,"abstract":"<p>Recent years have seen an exponential rise in data produced by Internet of Things (IoT) applications. Cloud servers were not designed for such extensive data, leading to challenges like increased makespan, cost, bandwidth, energy consumption, and network latency. To address these, the cloud–fog environment has emerged as an extension to cloud servers, offering services closer to IoT devices. Scheduling workflow applications to optimize multiple conflicting objectives in cloud fog is an NP-hard problem. Particle Swarm Optimization (PSO) is a good choice for multi-objective solutions due to its simplicity and rapid convergence. However, it has shortcomings like premature convergence and stagnation. To address these challenges, we formalize a theoretical background for scheduling workflow applications in the cloud–fog environment with multiple conflicting objectives. Subsequently, we propose an adaptive particle swarm optimization (APSO) algorithm with novel enhancements, including an S-shaped sigmoid function to dynamically decrease inertia weight and a linear updating mechanism for cognitive factors. Their integration in cloud–fog environments has not been previously explored. This novel application addresses unique challenges of workflow scheduling in cloud–fog systems, such as heterogeneous resource management, energy consumption, and increased cost. The effectiveness of APSO is evaluated using a real-world scientific workflow in a simulated cloud–fog environment and compared with four meta-heuristics. Our proposed workflow scheduling significantly reduces makespan and energy consumption without compromising overall cost compared to other meta-heuristics.</p>","PeriodicalId":10718,"journal":{"name":"Computing","volume":null,"pages":null},"PeriodicalIF":3.7,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141869709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hybrid networks, benefiting from both CNNs and Transformers architectures, exhibit stronger feature extraction capabilities compared to standalone CNNs or Transformers. However, in hybrid networks, the lack of attention in CNNs or insufficient refinement in attention mechanisms hinder the highlighting of target regions. Additionally, the computational cost of self-attention in Transformers poses a challenge to further improving network performance. To address these issues, we propose a novel point-to-point Dynamic Attention Guider(DAG) that dynamically generates multi-scale large receptive field attention to guide CNN networks to focus on target regions. Building upon DAG, we introduce a new hybrid network called the Dynamic Attention Guider Network (DAGN), which effectively combines Dynamic Attention Guider Block (DAGB) modules with Transformers to alleviate the computational cost of self-attention in processing high-resolution input images. Extensive experiments demonstrate that the proposed network outperforms existing state-of-the-art models across various downstream tasks. Specifically, the network achieves a Top-1 classification accuracy of 88.3% on ImageNet1k. For object detection and instance segmentation on COCO, it respectively surpasses the best FocalNet-T model by 1.6 (AP^b) and 1.5 (AP^m), while achieving a top performance of 48.2% in semantic segmentation on ADE20K.
{"title":"Dynamic attention guider network","authors":"Chunguang Yue, Jinbao Li, Qichen Wang, Donghuan Zhang","doi":"10.1007/s00607-024-01328-4","DOIUrl":"https://doi.org/10.1007/s00607-024-01328-4","url":null,"abstract":"<p>Hybrid networks, benefiting from both CNNs and Transformers architectures, exhibit stronger feature extraction capabilities compared to standalone CNNs or Transformers. However, in hybrid networks, the lack of attention in CNNs or insufficient refinement in attention mechanisms hinder the highlighting of target regions. Additionally, the computational cost of self-attention in Transformers poses a challenge to further improving network performance. To address these issues, we propose a novel point-to-point Dynamic Attention Guider(DAG) that dynamically generates multi-scale large receptive field attention to guide CNN networks to focus on target regions. Building upon DAG, we introduce a new hybrid network called the Dynamic Attention Guider Network (DAGN), which effectively combines Dynamic Attention Guider Block (DAGB) modules with Transformers to alleviate the computational cost of self-attention in processing high-resolution input images. Extensive experiments demonstrate that the proposed network outperforms existing state-of-the-art models across various downstream tasks. Specifically, the network achieves a Top-1 classification accuracy of 88.3% on ImageNet1k. For object detection and instance segmentation on COCO, it respectively surpasses the best FocalNet-T model by 1.6 <span>(AP^b)</span> and 1.5 <span>(AP^m)</span>, while achieving a top performance of 48.2% in semantic segmentation on ADE20K.</p>","PeriodicalId":10718,"journal":{"name":"Computing","volume":null,"pages":null},"PeriodicalIF":3.7,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141869711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the development of IoT, the concept of intelligent services has gradually come to the fore. Intelligent services usually involve a large number of computation intensive tasks with data dependencies that are often modelled as directed acyclic graphs (DAGs), and the offloading of DAG tasks is complex and has proven to be an NP hard challenge. As a key research issue, the task offloading process migrates the computation intensive tasks from resource-constrained IoT devices to nearby edge servers, and pursuing a lower delay and energy consumption. However, data dependencies among tasks are complex, and it is challenging to coordinate the computation intensive tasks among multiple edge servers. In this paper, a flexible and generic DAG task model is built to support the associative task offloading process with complex data dependencies in IoT edge computing environments. Additionally, a priority-based DAG task offloading algorithm and a secondary resource allocation algorithm are proposed to minimize the response delay and improve the resource utilization of edge servers. Experimental results demonstrate that the proposed method can well support the DAG task offloading process with the shortest response delay, while outperforming all the benchmark policies, which is suitable for IoT edge computing environments.
随着物联网的发展,智能服务的概念逐渐凸显出来。智能服务通常涉及大量具有数据依赖关系的计算密集型任务,这些任务通常被建模为有向无环图(DAG),而 DAG 任务的卸载非常复杂,已被证明是一项 NP 难度很高的挑战。作为一个关键研究课题,任务卸载过程将计算密集型任务从资源受限的物联网设备迁移到附近的边缘服务器,并追求更低的延迟和能耗。然而,任务之间的数据依赖关系非常复杂,在多个边缘服务器之间协调计算密集型任务具有挑战性。本文建立了一个灵活通用的 DAG 任务模型,以支持物联网边缘计算环境中具有复杂数据依赖性的关联任务卸载过程。此外,本文还提出了基于优先级的 DAG 任务卸载算法和二次资源分配算法,以最大限度地减少响应延迟并提高边缘服务器的资源利用率。实验结果表明,所提出的方法能以最短的响应延迟很好地支持 DAG 任务卸载过程,同时性能优于所有基准策略,适用于物联网边缘计算环境。
{"title":"Priority-based DAG task offloading and secondary resource allocation in IoT edge computing environments","authors":"Yishan Chen, Xiansong Luo, Peng Liang, Junxiao Han, Zhonghui Xu","doi":"10.1007/s00607-024-01327-5","DOIUrl":"https://doi.org/10.1007/s00607-024-01327-5","url":null,"abstract":"<p>With the development of IoT, the concept of intelligent services has gradually come to the fore. Intelligent services usually involve a large number of computation intensive tasks with data dependencies that are often modelled as directed acyclic graphs (DAGs), and the offloading of DAG tasks is complex and has proven to be an NP hard challenge. As a key research issue, the task offloading process migrates the computation intensive tasks from resource-constrained IoT devices to nearby edge servers, and pursuing a lower delay and energy consumption. However, data dependencies among tasks are complex, and it is challenging to coordinate the computation intensive tasks among multiple edge servers. In this paper, a flexible and generic DAG task model is built to support the associative task offloading process with complex data dependencies in IoT edge computing environments. Additionally, a priority-based DAG task offloading algorithm and a secondary resource allocation algorithm are proposed to minimize the response delay and improve the resource utilization of edge servers. Experimental results demonstrate that the proposed method can well support the DAG task offloading process with the shortest response delay, while outperforming all the benchmark policies, which is suitable for IoT edge computing environments.</p>","PeriodicalId":10718,"journal":{"name":"Computing","volume":null,"pages":null},"PeriodicalIF":3.7,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141869712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-29DOI: 10.1007/s00607-024-01324-8
Ole Delzer, Richard Hobeck, Ingo Weber, Dominik Kaaser, Michael Sober, Stefan Schulte
The growing popularity of blockchains highlights the need to improve their scalability. While previous research has focused on scaling transaction processing, the scalability of transaction creation remains unexplored. This issue is particularly important for organizations needing to send large volumes of transactions quickly or continuously. Scaling transaction creation is challenging, especially for blockchain platforms like Ethereum, which require transactions to include a sequence number. This paper proposes four different methods to scale transaction creation. Our experimental evaluation assesses the scalability and latency of these methods, identifying two as feasible for scaling transaction creation. Additionally, we provide an in-depth theoretical analysis of these two methods.
{"title":"Analysis of strategies for scalable transaction creation in blockchains","authors":"Ole Delzer, Richard Hobeck, Ingo Weber, Dominik Kaaser, Michael Sober, Stefan Schulte","doi":"10.1007/s00607-024-01324-8","DOIUrl":"https://doi.org/10.1007/s00607-024-01324-8","url":null,"abstract":"<p>The growing popularity of blockchains highlights the need to improve their scalability. While previous research has focused on scaling transaction processing, the scalability of transaction creation remains unexplored. This issue is particularly important for organizations needing to send large volumes of transactions quickly or continuously. Scaling transaction creation is challenging, especially for blockchain platforms like Ethereum, which require transactions to include a sequence number. This paper proposes four different methods to scale transaction creation. Our experimental evaluation assesses the scalability and latency of these methods, identifying two as feasible for scaling transaction creation. Additionally, we provide an in-depth theoretical analysis of these two methods.</p>","PeriodicalId":10718,"journal":{"name":"Computing","volume":null,"pages":null},"PeriodicalIF":3.7,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141869710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-24DOI: 10.1007/s00607-024-01321-x
Luís Cruz-Filipe, Sofia Kostopoulou, Fabrizio Montesi, Jonas Vistrup
Lead generation refers to the identification of potential topics (the ‘leads’) of importance for journalists to report on. In this article we present (mu )XL, a new lead generation tool based on a microservice architecture that includes a component of explainable AI. (mu )XL collects and stores historical and real-time data from web sources, like Google Trends, and generates current and future leads. Leads are produced by a novel engine for hypothetical reasoning based on temporal logical rules, which can identify propositions that may hold depending on the outcomes of future events. This engine also supports additional features that are relevant for lead generation, such as user-defined predicates (allowing useful custom atomic propositions to be defined as Java functions) and negation (needed to specify and reason about leads characterized by the absence of specific properties). Our microservice architecture is designed using state-of-the-art methods and tools for API design and implementation, namely API patterns and the Jolie programming language. Thus, our development provides an additional validation of their usefulness in a new application domain (journalism). We also carry out an empirical evaluation of our tool.
线索生成指的是为记者确定重要的潜在报道主题("线索")。在这篇文章中,我们将介绍一个基于微服务架构的新型线索生成工具--(mu )XL,其中包括一个可解释的人工智能组件。(mu)XL 收集并存储来自谷歌趋势等网络来源的历史和实时数据,并生成当前和未来的线索。线索由一个基于时间逻辑规则的新颖假设推理引擎生成,它可以根据未来事件的结果确定可能成立的命题。该引擎还支持与线索生成相关的其他功能,如用户自定义谓词(允许将有用的自定义原子命题定义为 Java 函数)和否定(需要指定和推理以不存在特定属性为特征的线索)。我们的微服务架构设计采用了最先进的 API 设计和实施方法与工具,即 API 模式和 Jolie 编程语言。因此,我们的开发提供了在新应用领域(新闻业)中对其实用性的额外验证。我们还对我们的工具进行了实证评估。
{"title":"$$mu $$ XL: explainable lead generation with microservices and hypothetical answers","authors":"Luís Cruz-Filipe, Sofia Kostopoulou, Fabrizio Montesi, Jonas Vistrup","doi":"10.1007/s00607-024-01321-x","DOIUrl":"https://doi.org/10.1007/s00607-024-01321-x","url":null,"abstract":"<p>Lead generation refers to the identification of potential topics (the ‘leads’) of importance for journalists to report on. In this article we present <span>(mu )</span>XL, a new lead generation tool based on a microservice architecture that includes a component of explainable AI. <span>(mu )</span>XL collects and stores historical and real-time data from web sources, like Google Trends, and generates current and future leads. Leads are produced by a novel engine for hypothetical reasoning based on temporal logical rules, which can identify propositions that may hold depending on the outcomes of future events. This engine also supports additional features that are relevant for lead generation, such as user-defined predicates (allowing useful custom atomic propositions to be defined as Java functions) and negation (needed to specify and reason about leads characterized by the absence of specific properties). Our microservice architecture is designed using state-of-the-art methods and tools for API design and implementation, namely API patterns and the Jolie programming language. Thus, our development provides an additional validation of their usefulness in a new application domain (journalism). We also carry out an empirical evaluation of our tool.</p>","PeriodicalId":10718,"journal":{"name":"Computing","volume":null,"pages":null},"PeriodicalIF":3.7,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141778641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-21DOI: 10.1007/s00607-024-01319-5
Nermin Kartli, Erkan Bostanci, Mehmet Serdar Guzel
Several problems involving uncertainties can be modeled with fuzzy numbers according to the type of these uncertainties. It is natural to express the solution to such a problem with fuzzy numbers. In this study, we consider the fully fuzzy transportation problem. All input parameters of the problem are expressed with fuzzy numbers given in the parametric form. We propose a new heuristic algorithm to approximate the fuzzy optimal solution. The fuzzy problem is solved by transforming it into two independent parametric problems with the proposed method. We first divide the interval [0, 1] into a sufficiently large number of equal intervals, then write a linear programming problem for each partition point and solve these problems by transforming them into transportation problems. The proposed algorithm is supported by examples.
{"title":"Heuristic algorithm for an optimal solution of fully fuzzy transportation problem","authors":"Nermin Kartli, Erkan Bostanci, Mehmet Serdar Guzel","doi":"10.1007/s00607-024-01319-5","DOIUrl":"https://doi.org/10.1007/s00607-024-01319-5","url":null,"abstract":"<p>Several problems involving uncertainties can be modeled with fuzzy numbers according to the type of these uncertainties. It is natural to express the solution to such a problem with fuzzy numbers. In this study, we consider the fully fuzzy transportation problem. All input parameters of the problem are expressed with fuzzy numbers given in the parametric form. We propose a new heuristic algorithm to approximate the fuzzy optimal solution. The fuzzy problem is solved by transforming it into two independent parametric problems with the proposed method. We first divide the interval [0, 1] into a sufficiently large number of equal intervals, then write a linear programming problem for each partition point and solve these problems by transforming them into transportation problems. The proposed algorithm is supported by examples.</p>","PeriodicalId":10718,"journal":{"name":"Computing","volume":null,"pages":null},"PeriodicalIF":3.7,"publicationDate":"2024-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141737350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Attack detection in cyber security systems is one of the complex tasks which require domain specific knowledge and cognitive intelligence to detect novel and unknown attacks from large scale network data. This research explores how the network operations and network security affects the detection of unknown attacks in network systems. A hash based profile matching technique is presented in this paper for attack detection. The main objective of this work is to detect unknown attacks using a profile matching approach in Hypervisors. Hypervisors are characterized by their versatile nature since they allow the utilization of available system resources. The virtual machines (VMs) in the hypervisors are not dependent on the host hardware and as a result, hypervisors are considered advantageous. In addition, hypervisors have direct access to the hardware resources such as memory, storage and processors. However, hypervisors are more susceptible to the security threats which attack each and every VM. A SHA3-512 hashing algorithm used for generating hash values in hypervisor and the proposed model is used to verify whether the profile is malicious or benign. The performance of the hashbased profile matching technique is compared with traditional hash techniques namely SHA-256 and MD5 algorithm. Results show that the proposed SHA3-512 algorithm achieves a phenomenal performance in terms of phenomenal accuracy and zero false positive rates. Simulation results also show that the computation time required by Sha3-512 algorithm is lower compared to SHA-256 and MD5 algorithms. The performance analysis validates that the hash based approach achieves reliable performance for attack detection. The effectiveness of the hashing technique was determined using three different evaluation metrics namely attack DR, FPR, and computational time. Simulation results show that the existing SHA3- 512 algorithm detection rate of 97.24% with zero false positive rate and faster computational time compared to SHA 256 and MD5 algorithms.
{"title":"Efficient hashing technique for malicious profile detection at hypervisor environment","authors":"Anumukonda Naga Seshu Kumar, Rajesh Kumar Yadav, Nallanthighal Srinivasa Raghava","doi":"10.1007/s00607-024-01325-7","DOIUrl":"https://doi.org/10.1007/s00607-024-01325-7","url":null,"abstract":"<p>Attack detection in cyber security systems is one of the complex tasks which require domain specific knowledge and cognitive intelligence to detect novel and unknown attacks from large scale network data. This research explores how the network operations and network security affects the detection of unknown attacks in network systems. A hash based profile matching technique is presented in this paper for attack detection. The main objective of this work is to detect unknown attacks using a profile matching approach in Hypervisors. Hypervisors are characterized by their versatile nature since they allow the utilization of available system resources. The virtual machines (VMs) in the hypervisors are not dependent on the host hardware and as a result, hypervisors are considered advantageous. In addition, hypervisors have direct access to the hardware resources such as memory, storage and processors. However, hypervisors are more susceptible to the security threats which attack each and every VM. A SHA3-512 hashing algorithm used for generating hash values in hypervisor and the proposed model is used to verify whether the profile is malicious or benign. The performance of the hashbased profile matching technique is compared with traditional hash techniques namely SHA-256 and MD5 algorithm. Results show that the proposed SHA3-512 algorithm achieves a phenomenal performance in terms of phenomenal accuracy and zero false positive rates. Simulation results also show that the computation time required by Sha3-512 algorithm is lower compared to SHA-256 and MD5 algorithms. The performance analysis validates that the hash based approach achieves reliable performance for attack detection. The effectiveness of the hashing technique was determined using three different evaluation metrics namely attack DR, FPR, and computational time. Simulation results show that the existing SHA3- 512 algorithm detection rate of 97.24% with zero false positive rate and faster computational time compared to SHA 256 and MD5 algorithms.</p>","PeriodicalId":10718,"journal":{"name":"Computing","volume":null,"pages":null},"PeriodicalIF":3.7,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141745628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-17DOI: 10.1007/s00607-024-01326-6
Agyemang Paul, Yuxuan Wan, Zhefu Wu, Boyu Chen, Shufeng Gong
Deep neural networks are vulnerable to attacks, posing significant security concerns across various applications, particularly in computer vision. Adversarial training has demonstrated effectiveness in improving the robustness of deep learning models by incorporating perturbations into the input space during training. Recently, adversarial training has been successfully applied to deep recommender systems. In these systems, user and item embeddings are perturbed through a minimax game, with constraints on perturbation directions, to enhance the model’s robustness and generalization. However, they still fail to defend against iterative attacks, which have shown an over 60% increase in effectiveness in the computer vision domain. Deep recommender systems may therefore be more susceptible to iterative attacks, which might lead to generalization failures. In this paper, we adapt iterative examples for deep recommender systems. Specifically, we propose a Deep Recommender with Iteration Directional Adversarial Training (DRIDAT) that combines attention mechanism and directional adversarial training for recommendations. Firstly, we establish a consumer-product collaborative attention to convey consumers different preferences on their interested products and the distinct preferences of different consumers on the same product they like. Secondly, we train the DRIDAT objective function using adversarial learning to minimize the impact of iterative attack. In addition, the maximum direction attack could push the embedding vector of input attacks towards instances with distinct labels. We mitigate this problem by implementing suitable constraints on the direction of the attack. Finally, we perform a series of evaluations on two prominent datasets. The findings show that our methodology outperforms all other methods for all metrics.
{"title":"Deep recommendation with iteration directional adversarial training","authors":"Agyemang Paul, Yuxuan Wan, Zhefu Wu, Boyu Chen, Shufeng Gong","doi":"10.1007/s00607-024-01326-6","DOIUrl":"https://doi.org/10.1007/s00607-024-01326-6","url":null,"abstract":"<p>Deep neural networks are vulnerable to attacks, posing significant security concerns across various applications, particularly in computer vision. Adversarial training has demonstrated effectiveness in improving the robustness of deep learning models by incorporating perturbations into the input space during training. Recently, adversarial training has been successfully applied to deep recommender systems. In these systems, user and item embeddings are perturbed through a minimax game, with constraints on perturbation directions, to enhance the model’s robustness and generalization. However, they still fail to defend against iterative attacks, which have shown an over 60% increase in effectiveness in the computer vision domain. Deep recommender systems may therefore be more susceptible to iterative attacks, which might lead to generalization failures. In this paper, we adapt iterative examples for deep recommender systems. Specifically, we propose a Deep Recommender with Iteration Directional Adversarial Training (DRIDAT) that combines attention mechanism and directional adversarial training for recommendations. Firstly, we establish a consumer-product collaborative attention to convey consumers different preferences on their interested products and the distinct preferences of different consumers on the same product they like. Secondly, we train the DRIDAT objective function using adversarial learning to minimize the impact of iterative attack. In addition, the maximum direction attack could push the embedding vector of input attacks towards instances with distinct labels. We mitigate this problem by implementing suitable constraints on the direction of the attack. Finally, we perform a series of evaluations on two prominent datasets. The findings show that our methodology outperforms all other methods for all metrics.</p>","PeriodicalId":10718,"journal":{"name":"Computing","volume":null,"pages":null},"PeriodicalIF":3.7,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141717893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-10DOI: 10.1007/s00607-024-01317-7
D. N. Sachin, B. Annappa, Sateesh Ambesange
Various hospitals have adopted digital technologies in the healthcare sector for various healthcare-related applications. Due to the effect of the Covid-19 pandemic, digital transformation has taken place in many domains, especially in the healthcare domain; it has streamlined various healthcare activities. With the advancement in technology concept of telemedicine evolved over the years and led to personalized healthcare and drug discovery. The use of machine learning (ML) technique in healthcare enables healthcare professionals to make a more accurate and early diagnosis. Training these ML models requires a massive amount of data, including patients’ personal data, that need to be protected from unethical use. Sharing these data to train ML models may violate data privacy. A distributed ML paradigm called federated learning (FL) has allowed different medical research institutions, hospitals, and healthcare devices to train ML models without sharing raw data. This survey paper overviews existing research work on FL-related use cases and applications. This paper also discusses the state-of-the-art tools and techniques available for FL research, current shortcomings, and future challenges in using FL in healthcare.
各种医院已在医疗保健领域采用数字技术,用于各种医疗保健相关应用。由于 Covid-19 大流行病的影响,许多领域,尤其是医疗保健领域都发生了数字化转型;它简化了各种医疗保健活动。随着技术的进步,远程医疗的概念也在不断发展,并带来了个性化医疗和药物研发。在医疗保健领域使用机器学习(ML)技术可使医疗保健专业人员做出更准确、更早期的诊断。训练这些 ML 模型需要大量数据,包括患者的个人数据,这些数据需要得到保护,以免被不道德地使用。共享这些数据来训练 ML 模型可能会侵犯数据隐私。一种被称为联合学习(FL)的分布式 ML 范式允许不同的医学研究机构、医院和医疗设备在不共享原始数据的情况下训练 ML 模型。本调查报告概述了 FL 相关用例和应用的现有研究工作。本文还讨论了可用于 FL 研究的最先进工具和技术、当前的不足以及在医疗保健领域使用 FL 的未来挑战。
{"title":"Federated learning for digital healthcare: concepts, applications, frameworks, and challenges","authors":"D. N. Sachin, B. Annappa, Sateesh Ambesange","doi":"10.1007/s00607-024-01317-7","DOIUrl":"https://doi.org/10.1007/s00607-024-01317-7","url":null,"abstract":"<p>Various hospitals have adopted digital technologies in the healthcare sector for various healthcare-related applications. Due to the effect of the Covid-19 pandemic, digital transformation has taken place in many domains, especially in the healthcare domain; it has streamlined various healthcare activities. With the advancement in technology concept of telemedicine evolved over the years and led to personalized healthcare and drug discovery. The use of machine learning (ML) technique in healthcare enables healthcare professionals to make a more accurate and early diagnosis. Training these ML models requires a massive amount of data, including patients’ personal data, that need to be protected from unethical use. Sharing these data to train ML models may violate data privacy. A distributed ML paradigm called federated learning (FL) has allowed different medical research institutions, hospitals, and healthcare devices to train ML models without sharing raw data. This survey paper overviews existing research work on FL-related use cases and applications. This paper also discusses the state-of-the-art tools and techniques available for FL research, current shortcomings, and future challenges in using FL in healthcare.</p>","PeriodicalId":10718,"journal":{"name":"Computing","volume":null,"pages":null},"PeriodicalIF":3.7,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141587884","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}