物联网(Internet of Things,IoT)技术的发展给工业界和日常生活带来便利的同时,海量易受到各种攻击和破坏的IoT设备也降低了分布式拒绝服务(Distributed Denial of Service,DDoS)攻击发起的成本,使被攻击方无法响应正常用户访问.为了在...物联网(Internet of Things,IoT)技术的发展给工业界和日常生活带来便利的同时,海量易受到各种攻击和破坏的IoT设备也降低了分布式拒绝服务(Distributed Denial of Service,DDoS)攻击发起的成本,使被攻击方无法响应正常用户访问.为了在物联网边缘中快速、准确地完成DDoS攻击检测,弥补现有方法资源开销大、不精确的缺陷,本文提出了一种基于轻量化卷积神经网络(Lightweight Convolutional Neural Networks,LCNN)的DDoS检测方法.面向物联网流量特性,方法首先提取包级特征和经冗余分析筛选得到的流级特征.之后设计了低参数和运算量的卷积神经网络LCNN,最后基于变维后的特征,快速检测定位攻击.实验结果表明,方法检测准确率达99.4%.同时LCNN在FPGA中能够以较少的资源消耗,保证在1ms时间内完成对一条流的推理判断.展开更多
网络流量分类在网络管理和安全中至关重要,尤其是精准识别分布式拒绝服务(Distributed Denial of Service,DDoS)攻击这一威胁。DDoS攻击会导致服务中断、资源耗尽和经济损失,严重影响服务质量(QoS)。尽管集中式模型在DDoS攻击检测中取...网络流量分类在网络管理和安全中至关重要,尤其是精准识别分布式拒绝服务(Distributed Denial of Service,DDoS)攻击这一威胁。DDoS攻击会导致服务中断、资源耗尽和经济损失,严重影响服务质量(QoS)。尽管集中式模型在DDoS攻击检测中取得了一定成效,但在实际应用中存在挑战:数据分布不均、数据集中传输困难,以及异构设备和动态网络环境的限制,从而难以实现实时检测。为应对这些问题,本文提出了一种基于异步个性化联邦学习的DDoS攻击检测与缓解方法AdaPerFed(Adaptive Personalized Federated Learning)。首先,通过定制的ResNet架构高效处理一维流量数据,并集成Net模块增强特征提取能力。然后,通过软件定义网络(SDN,Software-Defined Networking)模拟复杂动态网络环境,并引入完善的缓解系统应对多样化攻击场景。个性化联邦学习框架有效处理了非独立同分布(Non-IID,Non-Independent and Identically Distributed)数据问题,并通过异步学习机制适应异构设备和网络条件的差异,提升了系统的鲁棒性和扩展性。实验结果表明,AdaPerFed在CICDDoS2019、CIC-IDS2017和InSDN等数据集上均优于其他联邦学习算法,在不同客户端数量下展现出更快的收敛速度和更强的鲁棒性,DDoS检测准确率提升了15%~20%。消融实验进一步验证了个性化聚合模块对系统性能的显著提升。展开更多
分布式拒绝服务(Distribute Denial of Service,DDoS)攻击是常见的网络攻击手段之一,对于影响力日益增长的区块链网络构成了较大的威胁。包含堆叠法(Stacking)在内的集成学习模型在DDoS攻击检测方面有很大前景,而Stacking在面对不同类...分布式拒绝服务(Distribute Denial of Service,DDoS)攻击是常见的网络攻击手段之一,对于影响力日益增长的区块链网络构成了较大的威胁。包含堆叠法(Stacking)在内的集成学习模型在DDoS攻击检测方面有很大前景,而Stacking在面对不同类型数据集时需要调整学习器组合。该文使用Stacking方法检测区块链DDoS攻击,利用贝叶斯优化确定各学习器超参数,同时还使用算术优化算法(Arithmetic Optimization Algorithm,AOA)选择基学习器的组合,来解决需要手动调节学习器的问题。在区块链网络攻击流量数据集和比特币交易所交易数据上分别进行了实验,通过准确率、攻击数据漏报率和宏平均精准率三种评价指标进行对比,该方法在这两种不同类型数据集上的性能均优于其他三种常见的集成学习算法。还通过改变实验数据集大小探究出攻击检测性能会随着数据集的增大而上升。通过实验可以证明该方法可以有效检测不同类型数据集上的区块链DDoS攻击。展开更多
[目的]DDoS攻击作为一种破坏性极强的网络威胁,严重影响电力系统的稳定运行。由于电力监控局域网中的数据流量复杂多变,DDoS攻击流量与正常流量在表现形式上存在较高相似性,导致二者难以有效区分。传统的静态阈值方法虽能在一定程度上...[目的]DDoS攻击作为一种破坏性极强的网络威胁,严重影响电力系统的稳定运行。由于电力监控局域网中的数据流量复杂多变,DDoS攻击流量与正常流量在表现形式上存在较高相似性,导致二者难以有效区分。传统的静态阈值方法虽能在一定程度上实现流量监测,但因无法适应流量的动态变化,常出现误判,从而削弱了对DDoS攻击的检测效果,难以为电力监控局域网提供可靠的安全保障。为此,提出一种基于动态阈值的电力监控局域网DDoS攻击检测方法。[方法]通过网络流量采集设备实时获取电力监控局域网的流量数据,并利用信息熵理论计算流量熵值。信息熵可反映数据的混乱程度:正常流量通常具有一定规律性,熵值相对稳定;而DDoS攻击流量因异常数据包的大量涌入,导致熵值显著波动。基于此特性,本文设定动态阈值,当流量熵值超过阈值时判定为异常流量。随后,提取异常流量的六元组特征集(包括平均流包数、平均字节数、源IP地址增速、流表生存时间变化、端口增速以及对流比),并将其输入预训练的最小二乘支持向量机(least squares support vector machine,LSSVM)分类器中。LSSVM通过对已知样本的学习建立特征与类别的映射关系,从而实现对异常流量的分类与判断,确定其是否为DDoS攻击流量。[结果]实验结果表明,本文方法在ROC曲线和PR曲线上均表现较好,ROC-AUC和PR-AUC值均较传统方法有所提高。这表明该方法在检测DDoS攻击时具备更高的准确率与召回率,能够有效识别隐藏于正常流量中的攻击流量,并显著降低误判率。[结论]基于动态阈值与LSSVM分类器的检测方法能够有效应对电力监控局域网中DDoS攻击与正常流量难以区分的问题,提升检测的准确性与可靠性,为电力监控局域网提供更为有效的DDoS攻击防护手段,有助于增强电力系统的安全性与稳定性,保障电力供应的可靠运行,对电力行业网络安全防护具有重要的实际应用价值。展开更多
分布式拒绝服务(distributed denial of service,DDoS)攻击是重要的安全威胁,网络速度的不断提高给传统的检测方法带来了新的挑战。以Spark等为代表的大数据处理技术,给网络安全的高速检测带来了新的契机。提出了一种基于Spark Streamin...分布式拒绝服务(distributed denial of service,DDoS)攻击是重要的安全威胁,网络速度的不断提高给传统的检测方法带来了新的挑战。以Spark等为代表的大数据处理技术,给网络安全的高速检测带来了新的契机。提出了一种基于Spark Streaming框架的自适应实时DDoS检测防御技术,通过对滑动窗口内源簇进行分组,并根据与各分组内源簇比例的偏差统计,检测出DDoS攻击流量。通过感知合法的网络流量,实现了对DDoS攻击的自适应快速检测和有效响应。实验结果表明,该技术可极大地提升检测能力,为保障网络服务性能和安全检测的可扩展性提供了一种可行的解决方案。展开更多
The explosive expansion of the Internet of Things(IoT)systems has increased the imperative to have strong and robust solutions to cyber Security,especially to curtail Distributed Denial of Service(DDoS)attacks,which c...The explosive expansion of the Internet of Things(IoT)systems has increased the imperative to have strong and robust solutions to cyber Security,especially to curtail Distributed Denial of Service(DDoS)attacks,which can cripple critical infrastructure.The proposed framework presented in the current paper is a new hybrid scheme that induces deep learning-based traffic classification and blockchain-enabledmitigation tomake intelligent,decentralized,and real-time DDoS countermeasures in an IoT network.The proposed model fuses the extracted deep features with statistical features and trains them by using traditional machine-learning algorithms,which makes them more accurate in detection than statistical features alone,based on the Convolutional Neural Network(CNN)architecture,which can extract deep features.A permissioned blockchain will be included to record the threat cases immutably and automatically execute mitigation measures through smart contracts to provide transparency and resilience.When tested on two test sets,BoT-IoT and IoT-23,the framework obtains a maximum F1-score at 97.5 percent and only a 1.8 percent false positive rate,which compares favorably to other solutions regarding effectiveness and the amount of time required to respond.Our findings support the feasibility of our method as an extensible and secure paradigm of nextgeneration IoT security,which has constrictive utility in mission-critical or resource-constrained settings.The work is a substantial milestone in autonomous and trustful mitigation against DDoS attacks through intelligent learning and decentralized enforcement.展开更多
Vehicular Ad Hoc Networks(VANETs)are central to Intelligent Transportation Systems(ITS),especially for real-time communication involving emergency vehicles.Yet,Distributed Denial of Service(DDoS)attacks can disrupt sa...Vehicular Ad Hoc Networks(VANETs)are central to Intelligent Transportation Systems(ITS),especially for real-time communication involving emergency vehicles.Yet,Distributed Denial of Service(DDoS)attacks can disrupt safety-critical channels and undermine reliability.This paper presents a robust,scalable framework for detecting DDoS attacks in highway VANETs.We construct a new dataset with Network Simulator 3(NS-3)and Simulation of Urban Mobility(SUMO),enriched with real mobility traces from Germany’s A81 highway(OpenStreetMap).Three traffic classes are modeled:DDoS,Voice over IP(VoIP),and Transmission Control Protocol Based(TCP-based)video streaming(VideoTCP).The pipeline includes normalization,feature selection with SHapley Additive exPlanations(SHAP),and class balancing via Synthetic Minority Over-sampling Technique(SMOTE).Eleven classifiers are benchmarked—including eXtreme Gradient Boosting(XGBoost),Categorical Boosting(CatBoost),Adaptive Boosting(AdaBoost),Gradient Boosting(GB),and an Artificial Neural Network(ANN)—using stratified 5-fold cross-validation.XGBoost,GB,CatBoost and ANN achieve the highest performance(weighted F1-score=97%).To assess robustness under non-ideal conditions,we introduce an adversarial evaluation with packet-loss and traffic-jitter(small-sample deformation);the top models retain strong performance,supporting real-time applicability.Collectively,these results demonstrate that the proposed highway-focused framework is accurate,resilient,and well-suited for deployment in VANET security for emergency communications.展开更多
The era of big data brings new challenges for information network systems(INS),simultaneously offering unprecedented opportunities for advancing intelligent intrusion detection systems.In this work,we propose a data-d...The era of big data brings new challenges for information network systems(INS),simultaneously offering unprecedented opportunities for advancing intelligent intrusion detection systems.In this work,we propose a data-driven intrusion detection system for Distributed Denial of Service(DDoS)attack detection.The system focuses on intrusion detection from a big data perceptive.As intelligent information processing methods,big data and artificial intelligence have been widely used in information systems.The INS system is an important information system in cyberspace.In advanced INS systems,the network architectures have become more complex.And the smart devices in INS systems collect a large scale of network data.How to improve the performance of a complex intrusion detection system with big data and artificial intelligence is a big challenge.To address the problem,we design a novel intrusion detection system(IDS)from a big data perspective.The IDS system uses tensors to represent large-scale and complex multi-source network data in a unified tensor.Then,a novel tensor decomposition(TD)method is developed to complete big data mining.The TD method seamlessly collaborates with the XGBoost(eXtreme Gradient Boosting)method to complete the intrusion detection.To verify the proposed IDS system,a series of experiments is conducted on two real network datasets.The results revealed that the proposed IDS system attained an impressive accuracy rate over 98%.Additionally,by altering the scale of the datasets,the proposed IDS system still maintains excellent detection performance,which demonstrates the proposed IDS system’s robustness.展开更多
文摘物联网(Internet of Things,IoT)技术的发展给工业界和日常生活带来便利的同时,海量易受到各种攻击和破坏的IoT设备也降低了分布式拒绝服务(Distributed Denial of Service,DDoS)攻击发起的成本,使被攻击方无法响应正常用户访问.为了在物联网边缘中快速、准确地完成DDoS攻击检测,弥补现有方法资源开销大、不精确的缺陷,本文提出了一种基于轻量化卷积神经网络(Lightweight Convolutional Neural Networks,LCNN)的DDoS检测方法.面向物联网流量特性,方法首先提取包级特征和经冗余分析筛选得到的流级特征.之后设计了低参数和运算量的卷积神经网络LCNN,最后基于变维后的特征,快速检测定位攻击.实验结果表明,方法检测准确率达99.4%.同时LCNN在FPGA中能够以较少的资源消耗,保证在1ms时间内完成对一条流的推理判断.
文摘[目的]DDoS攻击作为一种破坏性极强的网络威胁,严重影响电力系统的稳定运行。由于电力监控局域网中的数据流量复杂多变,DDoS攻击流量与正常流量在表现形式上存在较高相似性,导致二者难以有效区分。传统的静态阈值方法虽能在一定程度上实现流量监测,但因无法适应流量的动态变化,常出现误判,从而削弱了对DDoS攻击的检测效果,难以为电力监控局域网提供可靠的安全保障。为此,提出一种基于动态阈值的电力监控局域网DDoS攻击检测方法。[方法]通过网络流量采集设备实时获取电力监控局域网的流量数据,并利用信息熵理论计算流量熵值。信息熵可反映数据的混乱程度:正常流量通常具有一定规律性,熵值相对稳定;而DDoS攻击流量因异常数据包的大量涌入,导致熵值显著波动。基于此特性,本文设定动态阈值,当流量熵值超过阈值时判定为异常流量。随后,提取异常流量的六元组特征集(包括平均流包数、平均字节数、源IP地址增速、流表生存时间变化、端口增速以及对流比),并将其输入预训练的最小二乘支持向量机(least squares support vector machine,LSSVM)分类器中。LSSVM通过对已知样本的学习建立特征与类别的映射关系,从而实现对异常流量的分类与判断,确定其是否为DDoS攻击流量。[结果]实验结果表明,本文方法在ROC曲线和PR曲线上均表现较好,ROC-AUC和PR-AUC值均较传统方法有所提高。这表明该方法在检测DDoS攻击时具备更高的准确率与召回率,能够有效识别隐藏于正常流量中的攻击流量,并显著降低误判率。[结论]基于动态阈值与LSSVM分类器的检测方法能够有效应对电力监控局域网中DDoS攻击与正常流量难以区分的问题,提升检测的准确性与可靠性,为电力监控局域网提供更为有效的DDoS攻击防护手段,有助于增强电力系统的安全性与稳定性,保障电力供应的可靠运行,对电力行业网络安全防护具有重要的实际应用价值。
文摘分布式拒绝服务(distributed denial of service,DDoS)攻击是重要的安全威胁,网络速度的不断提高给传统的检测方法带来了新的挑战。以Spark等为代表的大数据处理技术,给网络安全的高速检测带来了新的契机。提出了一种基于Spark Streaming框架的自适应实时DDoS检测防御技术,通过对滑动窗口内源簇进行分组,并根据与各分组内源簇比例的偏差统计,检测出DDoS攻击流量。通过感知合法的网络流量,实现了对DDoS攻击的自适应快速检测和有效响应。实验结果表明,该技术可极大地提升检测能力,为保障网络服务性能和安全检测的可扩展性提供了一种可行的解决方案。
文摘The explosive expansion of the Internet of Things(IoT)systems has increased the imperative to have strong and robust solutions to cyber Security,especially to curtail Distributed Denial of Service(DDoS)attacks,which can cripple critical infrastructure.The proposed framework presented in the current paper is a new hybrid scheme that induces deep learning-based traffic classification and blockchain-enabledmitigation tomake intelligent,decentralized,and real-time DDoS countermeasures in an IoT network.The proposed model fuses the extracted deep features with statistical features and trains them by using traditional machine-learning algorithms,which makes them more accurate in detection than statistical features alone,based on the Convolutional Neural Network(CNN)architecture,which can extract deep features.A permissioned blockchain will be included to record the threat cases immutably and automatically execute mitigation measures through smart contracts to provide transparency and resilience.When tested on two test sets,BoT-IoT and IoT-23,the framework obtains a maximum F1-score at 97.5 percent and only a 1.8 percent false positive rate,which compares favorably to other solutions regarding effectiveness and the amount of time required to respond.Our findings support the feasibility of our method as an extensible and secure paradigm of nextgeneration IoT security,which has constrictive utility in mission-critical or resource-constrained settings.The work is a substantial milestone in autonomous and trustful mitigation against DDoS attacks through intelligent learning and decentralized enforcement.
文摘Vehicular Ad Hoc Networks(VANETs)are central to Intelligent Transportation Systems(ITS),especially for real-time communication involving emergency vehicles.Yet,Distributed Denial of Service(DDoS)attacks can disrupt safety-critical channels and undermine reliability.This paper presents a robust,scalable framework for detecting DDoS attacks in highway VANETs.We construct a new dataset with Network Simulator 3(NS-3)and Simulation of Urban Mobility(SUMO),enriched with real mobility traces from Germany’s A81 highway(OpenStreetMap).Three traffic classes are modeled:DDoS,Voice over IP(VoIP),and Transmission Control Protocol Based(TCP-based)video streaming(VideoTCP).The pipeline includes normalization,feature selection with SHapley Additive exPlanations(SHAP),and class balancing via Synthetic Minority Over-sampling Technique(SMOTE).Eleven classifiers are benchmarked—including eXtreme Gradient Boosting(XGBoost),Categorical Boosting(CatBoost),Adaptive Boosting(AdaBoost),Gradient Boosting(GB),and an Artificial Neural Network(ANN)—using stratified 5-fold cross-validation.XGBoost,GB,CatBoost and ANN achieve the highest performance(weighted F1-score=97%).To assess robustness under non-ideal conditions,we introduce an adversarial evaluation with packet-loss and traffic-jitter(small-sample deformation);the top models retain strong performance,supporting real-time applicability.Collectively,these results demonstrate that the proposed highway-focused framework is accurate,resilient,and well-suited for deployment in VANET security for emergency communications.
基金supported in part by the National Nature Science Foundation of China under Project 62166047in part by the Yunnan International Joint Laboratory of Natural Rubber Intelligent Monitor and Digital Applications under Grant 202403AP140001in part by the Xingdian Talent Support Program under Grant YNWR-QNBJ-2019-270.
文摘The era of big data brings new challenges for information network systems(INS),simultaneously offering unprecedented opportunities for advancing intelligent intrusion detection systems.In this work,we propose a data-driven intrusion detection system for Distributed Denial of Service(DDoS)attack detection.The system focuses on intrusion detection from a big data perceptive.As intelligent information processing methods,big data and artificial intelligence have been widely used in information systems.The INS system is an important information system in cyberspace.In advanced INS systems,the network architectures have become more complex.And the smart devices in INS systems collect a large scale of network data.How to improve the performance of a complex intrusion detection system with big data and artificial intelligence is a big challenge.To address the problem,we design a novel intrusion detection system(IDS)from a big data perspective.The IDS system uses tensors to represent large-scale and complex multi-source network data in a unified tensor.Then,a novel tensor decomposition(TD)method is developed to complete big data mining.The TD method seamlessly collaborates with the XGBoost(eXtreme Gradient Boosting)method to complete the intrusion detection.To verify the proposed IDS system,a series of experiments is conducted on two real network datasets.The results revealed that the proposed IDS system attained an impressive accuracy rate over 98%.Additionally,by altering the scale of the datasets,the proposed IDS system still maintains excellent detection performance,which demonstrates the proposed IDS system’s robustness.
