No abstract

In smart city infrastructure, IoT networks contain intelligent devices for collecting and processing data using open channel internet. Some challenges have occurred in the existing methods while transferring the data, like centralism, safety, secrecy (data destroying, inference attacks), transparency, scalability, verification, and controlling the rapid adaptation of smart cities. To overcome these challenges, a machine learning based block chain method is proposed in this manuscript. The machine learning strategies can process massive datasets. Furthermore, they contain adequate generalization to identify various attack vectors. Here, the block chain fostered cycle‐consistent generative adversarial network (CCGAN) framework espoused intrusion detection is proposed for protecting the IoT network. Also, a 3 level privacy model is introduced for protecting the IoT devices. The first level is block chain based privacy detection and the second level is CCGAN and the third level is classification. In first level, ToN‐IoT, BoT‐IoT datasets are taken to detect the IoT intrusion, these data's are given to the block chain to authenticate and to collect the data in the IoT devices in the smart cities and stored in the blocks present in the block chain. In second level, the feature mapping and feature selection are done. The normal and attacked instances are classified in level 3. The performance of the proposed method shows higher accuracy 25.37%, 29.57%, and 18.67%, higher recall 23.75%, 17.58%, and 14.68% better than the existing methods, like block chain and machine learning method based privacy protection in IoT using optimized gradient tree boosting system (IOT‐BC‐XGBoost), and block chain and machine learning method based privacy protection in IoT using deep gated recurrent neural network (IOT‐BC‐DGRNN), respectively.

MANET (mobile ad hoc network) comprises of a set of wireless mobile node connected in a self-healing and self-configured network devoid of any fixed infrastructure.The cognitive radio (CR) in the MANET system has been developed for addressing the spectrum congestion issue. However, the existing techniques failed to solves the complex convex problem of channel assignment. To address this issue, the proposed protocol is designed. In the proposed scheme, both primary user (PU) and secondary user (SU) are clustered initially based on the graph theory process. After that, in each cluster, formation of robust spatial Gabriel graph (RS-GG) takes place at which the neighboring nodes are predicted by estimating the weighted end-to-end delay. Once the multi path decision-making condition is satisfied, the route path is established, and the communication takes place based on QoS constraint. This can lead to the enhancement of PDR, network connectivity maintenance and network lifetime. The performance analysis of the proposed methods is carried out for PDR, control overheads, energy consumption, and End-to-End delay and the analysis is compared with existing protocols to prove the effectiveness of proposed design. The simulation outcomes illustrate that the suggested strategy performs well and improves the data transmission.

Security is of paramount importance in the number of systems affiliated with increased IoT. Therefore, in this manuscript, a Stacked Auto Encoder based Deep Neural Network (DNN) fostered Intrusion Detection Framework is proposed to secure the IoT Environment. Here, the data is given to the preprocessing stage, in which redundancy elimination and replacement of missing value are done. Then, the preprocessed output is given to the feature selection process. Wherein, the Golden eagle optimization (GEO) algorithm selects the optimum features from pre-processed data sets. Then selected features are given to the Stacked Auto encoder based deep neural network for classification, which classified the data, like normal, anomalies. Here, the proposed approach is implemented in Python language. To check the robustness of the proposed approach, the performance metrics, like accuracy, specificity, sensitivity, F-measure, precision, and recall is measured. The simulation outcome show that the proposed Stacked Auto Encoder based Deep Neural Network based Intrusion Detection Framework (IDS-FS-GEO-SAENN) method attains higher accuracy 99.

Cloud computing is the delivery of computing services including servers, storage, databases, networking, software, analytics, and intelligence over the internet ("the cloud") to offer faster innovation, flexible resources, and economies of scale. In this article, cycle-consistent generative adversarial network (CCGAN) optimized with water strider optimization (WSO) algorithm fostered intrusion detection system (IDS) is proposed to secure the cloud computing (CC) environment (IDS-CC-CCGAN-WSOA).Initially, the input data's are gathered via NSL-KDD benchmark dataset. Then it is given to preprocessing. During preprocessing, it debugs the redundancy and missing value is restored using local least squares. Then, the preprocessed output is fed to the feature selection level. The optimum features are compiled utilizing correlation feature selection approach. This optimum features based, the data's are categorized as normal and anomalous data. The weights of this network are optimized by water strider optimization to attain effectual and optimum solution for recognizing the intruders. The proposed approach is executed in MATLAB. The performance metrics is examined to validate the performance of the proposed approach. Finally, the proposed approach attains 13.9367%, 13.268%, and 13.739% higher accuracy analyzed to the existing approaches, such as IDS-CC-DBN-CSSA, IDS-CC-DNN-IGASAA, and IDS-CC-MLPNN-ABC.