共查询到20条相似文献，搜索用时 15 毫秒
1.
Detecting anomalies is crucial for maintaining security in Wireless Sensor Networks (WSNs), as they are susceptible to various attacks that compromise nodes and yield inaccurate outcomes. Conventional attack detection approaches face challenges like high false positives, vulnerability to complex attacks, and limited adaptability to changing attacks due to predefined patterns. Additionally, the computational strain on resource-constrained nodes hampers network efficiency, demanding innovative and resilient security solutions. Therefore, this research work introduces Novel Hybrid Approaches for Privacy-preserved Multiple Attacks Detection (NHAPMAD) framework in both network attack detection system and host attack detection system. This topology bolsters the network's defense against various types of attacks, thereby ensuring the preservation of sensitive data privacy. Federated learning has been incorporated into the NHAPMAD framework to protect user privacy in WSNs. The introduced framework provides better anomaly detection and reduces false alarms. Additionally, the introduced model protects sensitive data, ensuring the security and integrity of the entire WSN, promoting a stable and dependable operating environment. The introduced method exhibits superior performance across various metrics like overall accuracy (99.6%), F1-score (99.59%), recall (99.47%), precision (99.63%), detection rate (99.5%), processing time (0.0009 s), etc. compared to traditional approaches, marking a significant advancement in the realm of WSN security. 相似文献
2.
深度学习模型容易受到对抗样本的影响,在图像上添加肉眼不可见的微小扰动就可以使训练有素的深度学习模型失灵。最近的研究表明这种扰动也存在于现实世界中。聚焦于深度学习目标检测模型的物理对抗攻击,明确了物理对抗攻击的概念,并介绍了目标检测物理对抗攻击的一般流程,依据攻击任务的不同,从车辆检测和行人检测两个方面综述了近年来一系列针对目标检测网络的物理对抗攻击方法,简单介绍了其他针对目标检测模型的攻击、其他攻击任务和其他攻击方式。最后讨论了物理对抗攻击当前面临的挑战,引出了对抗训练的局限性,并展望了未来可能的发展方向和应用前景。 相似文献
3.
PTA工业生产过程中4-CBA的含量是评价其产品质量的重要依据。将深度置信网络和已有的浅层算法相结合,提出基于深度置信网络的4-CBA软测量模型。深度置信网络是一种典型的深度学习算法,该算法在特征学习方面优势显著。根据实验结果,基于深度置信网络的软测量模型能够很好地估计4-CBA含量,和单纯的BP神经网络模型相比,基于深度置信网络的模型预测精度更高。 相似文献
4.
Mohd Saqib Akhoon Shahrel A. Suandi Abdullah Alshahrani Abdul-Malik H. Y. Saad Fahad R. Albogamy Mohd Zaid Bin Abdullah Sajad A. Loan 《Expert Systems》2022,39(1):e12831
The availability of huge structured and unstructured data, advanced highly dense memory and high performance computing machines have provided a strong push for the development in artificial intelligence (AI) and machine learning (ML) domains. AI and machine learning has rekindled the hope of efficiently solving complex problems which was not possible in the recent past. The generation and availability of big-data is a strong driving force for the development of AI/ML applications, however, several challenges need to be addressed, like processing speed, memory requirement, high bandwidth, low latency memory access, and highly conductive and flexible connections between processing units and memory blocks. The conventional computing platforms are unable to address these issues with machine learning and AI. Deep neural networks (DNNs) are widely employed for machine learning and AI applications, like speech recognition, computer vison, robotics, and so forth, efficiently and accurately. However, accuracy is achieved at the cost of high computational complexity, sacrificing energy efficiency and throughput like performance measuring parameters along with high latency. To address the problems of latency, energy efficiency, complexity, power consumption, and so forth, a lot of state of the art DNN accelerators have been designed and implemented in the form of application specific integrated circuits (ASICs) and field programmable gate arrays (FPGAs). This work provides the state of the art of all these DNN accelerators which have been developed recently. Various DNN architectures, their computing units, emerging technologies used in improving the performance of DNN accelerators will be discussed. Finally, we will try to explore the scope for further improvement in these accelerator designs, various opportunities and challenges for the future research. 相似文献
5.
Wireless sensor network (WSN) works with a collection of multiple sensor nodes to fetch the data from the deployed environment to fulfill the application whether it is agricultural monitoring, industrial monitoring, etc. The agricultural region can be monitored by deploying sensor nodes to multiple verticals where continuous human presence is not feasible. These devices are equipped with limited resources and are easily vulnerable to various cyber-attacks. The attacker can hack the sensor nodes to steal critical information from WSN devices. The cluster heads in the WSN play a vital role in the process of routing data packets and attackers launch malicious codes through sender nodes to hack or damage the cluster heads to shut down the entire deployed network of agricultural regions. This research paper proposes a framework to improve the security of WSNs by providing a shield to the cluster heads of the network using machine learning techniques. The experimental study of the paper includes the comparative analysis of three machine learning techniques decision tree classifier, Gaussian Naïve Bayes, and random forest classifier for predicting WSN attacks like flooding, gray hole, blackhole, and TDMA that are deployed to support the proposed WSN security framework on the attack dataset. The random forest classifier achieves an accuracy of 98%, Precision of 97.6%, Recall of 97.6%, and F1 score of 97.8% which is the maximum among the deployed machine learning techniques. 相似文献
6.
数据收集是无线传感器网络的重要应用之一,其主要的工作过程可以概括为传感器节点将感知的信息通过一定的路径传送到无线网关节点进行进一步分析处理的过程.在数据收集时,由于人们无法预知事件触发的地点,常常将传感器均匀布置在监测的场所中,但是信息收集的地点往往是不均匀分布的,这就导致了一部分节点会因处在事件频发地段而持续的工作,而另一些节点却始终不会工作.为了解决这个问题,提出一个应用加强学习算法的自适应无线路由策略.在该路由策略中,路由的过程被当作分布式智能节点加强学习的过程.每一个传感器节点都是一个独立的智能节点,可以通过参数化的选择概率和回报来决定自己的下一跳地址.该策略的目的是使长时间不工作的节点代替长时间工作的节点传输数据,以达到平均节点能耗,延长整体网络寿命的效果.最后的仿真结果说明我们的路由策略可以有效的分散数据传输,延长网络寿命. 相似文献
7.
在无线传感器网络数据融合算法中,BP神经网络被广泛用于节点数据的特征提取和分类。为了解决BP神经网络收敛慢,易陷入局部最优值且泛化能力差从而影响数据融合效果的问题,提出一种将深度学习技术和分簇协议相结合的数据融合算法SAESMDA。SAESMDA用基于层叠自动编码器(SAE)的深度学习模型SAESM取代BP神经网络,算法首先在汇聚节点训练SAESM并对网络分簇,接着各簇节点通过SAESM对采集数据进行特征提取,之后由簇首将分类融合后的特征发送至汇聚节点。仿真实验表明,和采用BP神经网络的BPNDA算法相比,SAESMDA在网络能耗大致相同的情况下具有更高的特征提取分类正确率。 相似文献
8.
一种基于神经网络集成的规则学习算法 总被引：8，自引：0，他引：8
将神经网络集成与规则学习相结合,提出了一种基于神经网络集成的规则学习算法．该算法以神经网络集成作为规则学习的前端,利用其产生出规则学习所用的数据集,在此基础上进行规则学习．在UCl机器学习数据库上的实验结果表明,该算法可以产生泛化能力非常强的规则． 相似文献
9.
无线传感器网络技术一经提出,迅速得到学术界、工业界的广泛关注,在国防军事、环境监测、智能家居、健康护理等领域发挥着重要作用.身份认证是保障无线传感器网络实时访问的关键安全技术.基于增强的攻击者模型,提出一种被长期忽略的内部攻击威胁,对无线传感器网络环境下的两个代表性认证协议进行了安全性分析.指出Mir等人的协议无法抵抗内部攻击和智能卡丢失攻击,且未实现前向安全性;指出Fang等人的协议同样无法实现所声称的前向安全性特性,且对内部攻击和智能卡丢失攻击是脆弱的.针对协议具体失误之处,提出相应的解决方案.总结了7类应对内部攻击的解决方案.指出了现有方法的不足,提出了合理的解决方案. 相似文献
10.
提出了一种新的深度残差网络的拓展模块,有效提高了学习表示的鲁棒性.所提出的方法是一个简单的即插即用模块,即组卷积式编码-解码结构,它可以作为一个额外的信息过滤部件集成到原来的深度残差网络中.利用编码器的下采样来产生信息压缩过的特征图,解码器模块被驱动以产生激活准确的特征图,其能够突出显示输入图片中最具有判别力的区域,最... 相似文献
11.
罗配明 《单片机与嵌入式系统应用》2011,11(11):8-10
无线传感器网络大量应用在环境监测、目标跟踪、安全监控等领域,因此网络的自身定位是大多数应用的基础。常用的定位方法必须测量节点间的距离。为了预测距离值,根据实验获取的RSSI值与对应的距离值,先对实验数据进行滤波处理,建立面向Matlab神经网络工具箱的神经网络预测模型,利用神经网络的特性和Matlab工具箱的强大功能,通过实测数据对网络进行训练。预测结果表明,距离精度达到1 m之内。 相似文献
12.
图像的自动标注是图像检索领域一项基础而又富有挑战性的任务。深度学习算法自提出以来在图像和文本识别领域取得了巨大的成功,是一种解决"语义鸿沟"问题的有效方法。图像标注问题可以分解为基于图像与标签相关关系的基本图像标注和基于标注词汇共生关系的标注改善两个过程。文中将基本图像标注问题视为一个多标记学习问题,图像的标签先验知识作为深度神经网络的监督信息。在得到基本标注词汇的基础上,利用原始图像标签词汇的依赖关系与先验分布改善了图像的标注结果。最后将所提出的改进的深度学习模型应用于Corel和ESP图像数据集,验证了该模型框架及所提出的解决方案的有效性。 相似文献
13.
14.
近年来,机器学习逐渐成为推动各行业发展的一种关键技术。联邦学习通过融合本地数据训练和在线梯度迭代,实现了分布式安全多方机器学习中的模型泛化能力和数据隐私保护双提升。由于联邦学习模型需要投入大量的训练成本（包括算力、数据集等）,因此,对凝结了巨大经济价值的联邦学习模型进行所有权保护显得尤为重要。文章调研了现存的针对联邦学习模型的所有权保护方案,通过对两种模型指纹方案、8种黑盒模型水印方案和5种白盒模型水印方案的梳理,分析联邦学习模型所有权保护的研究现状。此外,文章结合深度神经网络模型所有权保护方法,对联邦学习模型所有权保护的未来研究方向进行展望。 相似文献
15.
16.
17.
采用无线传感器网络对温室进行监控,用同一套网络分别完成风、光、水、电、热和农药等的数据采集和环境控制,可有效提高农业集约化生产程度,简化系统复杂性,降低设备成本。 相似文献
18.
无线传感器网络安全问题浅析 总被引：1，自引：0，他引：1
无线传感器网络（WSN）是由一组传感器以自组织、多跳方式构成的无线网络,是一种全新的信息获取、处理和传输技术,集传感器技术、嵌入式计算技术、无线通信技术以及分布式信息处理技术于一体。随着无线传感器网络应用领域不断扩大,其安全问题也变得越来越重要。该文主要分析无线传感器网络协议栈各层所面临的安全性问题及相应解决方案。 相似文献
19.
传感器网络中节点的高失效性及其移动性使得原来的数据传输路径容易破裂,需要进行快速重路由,而rushing攻击是在重路由过程中比较可能出现的攻击方法。论文主要是研究无线传感器网络的安全重路由问题,就重路由过程中的rushing攻击提出了安全邻居探测、随机的路由请求转发和黑名单机制等几项防御措施,并将这些防御措施应用到了已有的协议中。最后通过仿真来评估这种方法的性能,结果表明这种方法能很好地防御rushing攻击。 相似文献
20.
Energy load forecasting plays an important role in the smart grid, which can affect the promoting energy production and consumption decision‐making processes. In this paper, the state‐of‐the‐art deep learning (DL) neural models are used in the short‐term load forecasting, including the multilayer perceptron (MLP), the convolutional neural network (CNN), and the long short‐term memory (LSTM). A novel loss function is proposed for the load forecasting, and two commonly used benchmarks are used to verify the validity of the proposed function. The simulation results show that the mean absolute percentage error (MAPE) of the proposed loss function is 19.63% lower than cross‐entropy and 2.34% lower than mean absolute error (MAE). We compared the mentioned neural networks in different aspects, and the results show that in energy load forecasting, CNN has superior performance than MLP and LSTM in terms of high accuracy and robustness to weather changes. 相似文献