An Enhanced Secure Deep Learning Algorithm for Fraud Detection in Wireless Communication

Sanober, Sumaya; Alam, Izhar; Pande, Sagar; Arslan, Farrukh; Rane, Kantilal Pitambar; Singh, Bhupesh Kumar; Khamparia, Aditya; Shabaz, Mohammad

doi:10.1155/2021/6079582

Cited by 75 publications

(43 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Polycom, or mobile TV, facilitates audio and video communications between two or more individuals in two or more locations. Kiosks in e-Health are selfcontained devices (usually PCs) that provide interactive information to users [18,19]. Interoperable e-Healthcare services apply databases in the form of local data warehouses or cloud storage to enable decentralized query-driven deci-sion support [5,6].…”

Section: Introductionmentioning

confidence: 99%

[Retracted] Dynamic Data Infrastructure Security for Interoperable e‐Healthcare Systems: A Semantic Feature‐Driven NoSQL Intrusion Attack Detection Model

Sreejith

Senthil

2022

BioMed Research International

View full text Add to dashboard Cite

The exponential rise in advanced software computing and low-cost hardware has broadened the horizon for the Internet of Medical Things (IoMT), interoperable e-Healthcare systems serving varied purposes including electronic healthcare records (EHRs) and telemedicine. However, being heterogeneous and dynamic in nature, their database security remains a challenge forever. Numerous intrusion attacks including bot-attack and malware have confined major classical databases towards e-Healthcare. Despite the robustness of NoSQL over the structured query language databases, the dynamic data nature over a heterogeneous environment makes it vulnerable to intrusion attacks, especially over interoperable e-Healthcare systems. Considering these challenges, this work proposed a first of its kind semantic feature-driven NoSQL intrusion attack (NoSQL-IA) detection model for interoperable e-Healthcare systems. This work assessed the efficacy of the different semantic feature-extraction methods like Word2Vec, Continuous Bag of Words, N-Skip Gram (SKG), Count Vectorizer, TF-IDF, and GLOVE towards NoSQL-IA prediction. Subsequently, to minimize computational exhaustion, different feature selection methods including Wilcoxon Rank Sum Test (WRST), significant predictor test, principal component analysis, Select K-Best, and variance threshold feature selection algorithms were employed. To alleviate the data imbalance problem, it applied different resampling methods including upsampling, downsampling, and synthetic minority oversampling technique (SMOTE) over the selected features. Later, Min–Max normalization was performed over the input feature vectors to alleviate any possibility of overfitting. Towards NoSQL-IA prediction, different machine learning methods like Multinomial Naïve Bayes, decision tree, logistic regression, support vector machine, k-NN, AdaBoost, Extra Tree Classifier, random forest ensemble, and XG-Boost were applied, which classified each input query as the regular query or the NoSQL-IA attack query. The depth performance assessment revealed that the use of Word2Vec features SKG in sync with VTFS feature selection and SMOTE resampling processed with the bootstrapped random forest classifier can provide the best performance in terms of high accuracy (98.86%), F-Measure (0.974), and area under the curve (AUC) (0.981), thus enabling it suitable for interoperable e-Healthcare database security.

show abstract

Section: Introductionmentioning

confidence: 99%

[Retracted] Dynamic Data Infrastructure Security for Interoperable e‐Healthcare Systems: A Semantic Feature‐Driven NoSQL Intrusion Attack Detection Model

Sreejith

Senthil

2022

BioMed Research International

View full text Add to dashboard Cite

show abstract

“…To simplify, the weight and bias coefficients are denoted as v k and the nonlinear activation function as c k ∈ S 3 , respectively, in the formula [11]. e channels of every one feature in y (i,j,z)ʹ are mapped to the feature map using the same shared weight coefficients.…”

Section: Internal Structures Of the Networkmentioning

confidence: 99%

A Metaheuristic Autoencoder Deep Learning Model for Intrusion Detector System

Pandey

Kumar

Lamin

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

A multichannel autoencoder deep learning approach is developed to address the present intrusion detection systems’ detection accuracy and false alarm rate. First, two separate autoencoders are trained with average traffic and assault traffic. The original samples and the two additional feature vectors comprise a multichannel feature vector. Next, a one-dimensional convolution neural network (CNN) learns probable relationships across channels to better discriminate between ordinary and attack traffic. Unaided multichannel characteristic learning and supervised cross-channel characteristic dependency are used to develop an effective intrusion detection model. The scope of this research is that the method described in this study may significantly minimize false positives while also improving the detection accuracy of unknown attacks, which is the focus of this paper. This research was done in order to improve intrusion detection prediction performance. The autoencoder can successfully reduce the number of features while also allowing for easy integration with different neural networks; it can reduce the time it takes to train a model while also improving its detection accuracy. An evolutionary algorithm is utilized to discover the ideal topology set of the CNN model to maximize the hyperparameters and improve the network’s capacity to recognize interchannel dependencies. This paper is based on the multichannel autoencoder’s effectiveness; the fourth experiment is a comparative analysis, which proves the benefits of the approach in this article by correlating it to the findings of various different intrusion detection methods. This technique outperforms previous intrusion detection algorithms in several datasets and has superior forecast accuracy.

show abstract

“…For example, the mainstream distributed systems Apache Spark and Apache Flink have adapted for the dimension table association scenario. Apache Spark proposed Spark Streaming to improve computing latency and provide stream computing support [14]. This computing model minimizes each elastic distributed dataset by splitting the unlimited streaming data into discrete (discredited) streams (Resilient Distributed Dataset, RDD) size, built microbatch data set, to achieve the effect similar to stream computing, and the delay of stream computing at this stage is 100 ms.…”

Section: Related Workmentioning

confidence: 99%

Novel Big Data Networking Framework Using Multihoming Optimization for Distributed Stream Computing

Godla

Joseph

Dhiman

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

One of the main technologies for big data networking framework is online multihoming optimization that is large-scale dimension table association technology in a distributed environment. It is often used in applications like real-time suggestion and research. Big data is concerned with the quality of large datasets that are distributed. These datasets demand sophisticated network technologies to adequately transmit massive share files. Dimension table association is the process of integrating multihoming stream data with offline stored dimension table data and executing data processing using novel big data frameworks, as described in this study. The current technological options for dimension table connection are assessed first, followed by accompanying optimization technologies and the design route of mainstream distributed engines. The dimension table data query is the one that has been optimized with the greatest performance. Nonetheless, the typical optimization approach is influenced by the dimension, table size, and the design route of the mainstream distributed engine—limits on data flow rate. Second, due to the limitations of existing optimization technologies for the overall consideration of the cluster in a distributed environment, a computing model suited for hybrid computing of offline batch data and real-time streaming data is provided, followed by a single-point reading. Dimension table data, the dimension table associated data technique for distribution and calculation after segmentation, and optimization of the dimension table associated calculation logic adapt to a larger dimension table scale and are no longer restricted to data connections. Since optimizing the query of dimension table, data is employed to reduce the I/O overhead and delay caused by querying dimension table in big data. Finally, both the suggested and standard dimension table association technologies are implemented on the Apache Flink stream computing engine. Through trials, the throughput and latency on data created by Alibaba’s “Double Eleven” are compared, demonstrating the usefulness of dimension table association techniques for Distributed Stream Computing optimization by utilizing multihoming networks.

show abstract

An Enhanced Secure Deep Learning Algorithm for Fraud Detection in Wireless Communication

Cited by 75 publications

References 12 publications

[Retracted] Dynamic Data Infrastructure Security for Interoperable e‐Healthcare Systems: A Semantic Feature‐Driven NoSQL Intrusion Attack Detection Model

[Retracted] Dynamic Data Infrastructure Security for Interoperable e‐Healthcare Systems: A Semantic Feature‐Driven NoSQL Intrusion Attack Detection Model

A Metaheuristic Autoencoder Deep Learning Model for Intrusion Detector System

Novel Big Data Networking Framework Using Multihoming Optimization for Distributed Stream Computing

Contact Info

Product

Resources

About