- Volume 9
- Issue 1
- (5) Articles
Navod Neranjan Thilakarathne
,
N.T Weerawarna
,
Rakesh Kumar Mahendran
The rapid growth of Information and Communication Technology (ICT) in the 21st century has resulted in the emergence of a novel technological paradigm; known as the Internet of Things, or IoT. The IoT, which is at the heart of today's smart infrastructure, aids in the creation of a ubiquitous network of things by simplifying interconnection between smart digital devices and enabling Machine to Machine (M2M) communication. As of now, there are numerous examples of IoT use cases available, assisting every person in this world towards making their lives easier and more convenient. The latest advancement of IoT in a variety of domains such as healthcare, smart city, smart agriculture has led to an exponential growth of cyber-attacks that targets these pervasive IoT environments, which can even lead to jeopardizing the lives of people; that is involved with it. In general, this IoT can be considered as every digital object that is connected to the Internet for intercommunication. Hence in this regard to analyze cyber threats that come through the Internet, here we are doing an experimental evaluation to analyze the requests, received to exploit the opened Secure Shell (SSH) connection service of an IoT device, which in our case a Raspberry Pi devices, which connected to the Internet for more than six consecutive days. By opening the SSH service on Raspberry Pi, it acts as a Honeypot device where we can log and retrieve all login attempt requests received to the SSH service opened. Inspired by evaluating the IoT security attacks that target objects in the pervasive IoT environment, after retrieving all the login requests made through the open SSH connection we then provide a comprehensive analysis along with our observations about the origin of the requests and the focus areas of intruders; in this study.
Read More
Doi: https://doi.org/10.54216/JCIM.090102
Vol. 9
Issue. 1
PP. 18-26, (2022)
Mohamed Elsharkawy
,
I.S. Farahat
Bank telemarketing is a prominent way of direct marketing approach in which the telemarketers ask possible clients by mobile phones for purchasing or subscribing to bank product or service. But the clients who are not interested in the offers or promotions by the bank telemarketing commonly face negative interaction owing to the thought of thinking the telemarketing as spam. Therefore, the recent developments of deep learning (DL) models can be used to realize the predictive models for bank telemarketing applications. This study develops an effective Archimedes Optimization with Deep Belief Network based Predictive (AOA-DBNP) for bank telemarketing applications. The proposed AOA-DBNP technique primarily undergoes pre-processing for transforming the data as to useful format. In addition, the AOA-DBNP technique involves the use of the DBN model for the prediction process and finally, the AOA is applied for tuning the hyperparameters of DBN technique. The utilization of AOA helps to optimally select the hyperparameters of the DBN model in such a way that the predictive performance gets improved to a maximum extent. To showcase the enhanced efficiency of the AOA-DBNP manner, a comprehensive comparative results analysis reported the better performance of the AOA-DBNP model.
Read More
Doi: https://doi.org/10.54216/JCIM.090103
Vol. 9
Issue. 1
PP. 27-39, (2022)
Mohammed I. Alghamdi
In the modern internet-connected society, technologies underpin almost every action in society. Although there have been positive effects of technologies in the organization, there have been forensic specialists indicating the issues and challenges with cyber security threats. The real-time conditions provide the capability of the organization in detecting, analyzing, and defending individuals against such threats. In this research project, the focus is on understanding the cyber security threats and the protection approaches to be utilized in safeguarding threats from financial institutions. With the Covid-19 pandemic, most of the financial firms, including Al Rajhi Bank, are utilizing technologies in their operations, and this has exposed them to cyber security threats. From the literature review conducted, the financial firms need to consider cyber security approaches including implementing triple DES, RSA, and blowfish algorithms in improving the security measures of the organizations.
Read More
Doi: https://doi.org/10.54216/JCIM.090101
Vol. 9
Issue. 1
PP. 8-17, (2022)
Abedallah Zaid Abualkishik
,
Ali A. Alwan
The province of wireless sensor network (WSN) is increasing continuously because of wide-ranging applications, namely, monitoring environmental conditions, military, and many other fields. But trust management in the WSN is the main objective as trust was utilized once cooperation among nodes becomes crucial to attaining reliable transmission. Thus, a new trust-based routing protocol is introduced to initiate secure routing. This study focuses on the design of Trust Aware Aquila Optimizer based Secure Data Transmission for Information Management (TAAO-SDTIM) in WSN. The presented TAAO-SDTIM model mainly intends to achieve maximum security and information management in WSN. The presented TAAO-SDTIM model determines optimum set of routes to base station (BS) utilizing a fitness function involving three parameters like residual energy (RE), distance to BS (DBS), and trust level (TL). The incorporation of the trust level of the nodes in the route selection process aids in appropriately selecting highly secure nodes in the data transmission procedure. For ensuring the enhanced performance of the TAAO-SDTIM model, a wide range of experiments are executed and the results pointed out the improved outcomes of the TAAO-SDTIM model over the other recent approaches.
Read More
Doi: https://doi.org/10.54216/JCIM.090104
Vol. 9
Issue. 1
PP. 40-51, (2022)
Heba M. Fadhil
,
Noor Q. Makhool
,
Muna M. Hummady
,
Zinah O. Dawood
Botnet detection develops a challenging problem in numerous fields such as order, cybersecurity, law, finance, healthcare, and so on. The botnet signifies the group of co-operated Internet connected devices controlled by cyber criminals for starting co-ordinated attacks and applying various malicious events. While the botnet is seamlessly dynamic with developing counter-measures projected by both network and host-based detection techniques, the convention techniques are failed to attain sufficient safety to botnet threats. Thus, machine learning approaches are established for detecting and classifying botnets for cybersecurity. This article presents a novel dragonfly algorithm with multi-class support vector machines enabled botnet detection for information security. For effectual recognition of botnets, the proposed model involves data pre-processing at the initial stage. Besides, the model is utilized for the identification and classification of botnets that exist in the network. In order to optimally adjust the SVM parameters, the DFA is utilized and consequently resulting in enhanced outcomes. The presented model has the ability in accomplishing improved botnet detection performance. A wide-ranging experimental analysis is performed and the results are inspected under several aspects. The experimental results indicated the efficiency of our model over existing methods.
Read More
Doi: https://doi.org/10.54216/JCIM.090106
Vol. 9
Issue. 1
PP. 68-79, (2022)
