by Michael M Kangethe and Elisha Odira Abade
Original Research
The need for simple secure substitution encryption algorithms has risen due to complexities derived from current encryption algorithms, which over-complicate the process through many sub-processes and consume more space than necessary. This also creates the need for a secure string encryption approach that can also be applied using a simple pen and paper to encrypt and decrypt messages between each other. In this paper we present a technique based on a Non-Deterministic directional NxNchart-based encryption cipher as a solution to this problem. This will be achieved by using a 2-dimensional N by N chart as the key while using a dynamically selected directional approach to generate both the cipher and plain-text.
Journal of Computer Sciences and Applications. 2020, 8(2), 56-61. DOI: 10.12691/jcsa-8-2-3
Pub. Date: September 23, 2020
2990 Views358 Downloads
by Yaser M. Banadaki
Original Research
This paper presents a systematic two-layer approach for detecting DNS over HTTPS (DoH) traffic and distinguishing Benign-DoH traffic from Malicious-DoH traffic using six machine learning algorithms. The capability of machine learning classifiers is evaluated considering their accuracy, precision, recall, and F-score, confusion matrices, ROC curves, and feature importance. The results show that LGBM and XGBoost algorithms outperform the other algorithms in almost all the classification metrics reaching the maximum accuracy of 100% in the classification tasks of layers 1 and 2. LGBM algorithms only misclassified one DoH traffic test as non-DoH out of 4000 test datasets. It has also found that out of 34 features extracted from the CIRA-CIC-DoHBrw-2020 dataset, SourceIP is the critical feature for classifying DoH traffic from non-DoH traffic in layer one followed by DestinationIP feature. However, only DestinationIP is an important feature for LGBM and gradient boosting algorithms when classifying Benign-DoH from Malicious-DoH traffic in layer 2.
Journal of Computer Sciences and Applications. 2020, 8(2), 46-55. DOI: 10.12691/jcsa-8-2-2
Pub. Date: August 20, 2020
6276 Views712 Downloads
by Michael M Kangethe and Robert Oboko
Original Research
This is the study and implementation of an association surveillance technology framework model for GSM mobile networks. This enables the efficient and automated identification of entity associations and potential relationships between several entities and events based on a hierarchy of interactions. The approach to this problem is to develop a weighted graph network G=(V(W),E) where V={w(SID1),w(SID2),…,w(SIDn)} wrepresents the association sore between the ShadowID represented as a node SID and the Person of interest(POI) represented as the root node. This model and algorithm are developed as an automated surveillance system framework that enables the tracking of individual entities ' relationships with others based on their interaction and by their physical proximity to the entity of interest. As the future of automated surveillance will not just include the collection of geographic and visual data but also intelligence on the particular entity's interaction log information from activity patterns which can be mapped in an easy to present format to the interested parties.
Journal of Computer Sciences and Applications. 2020, 8(2), 40-45. DOI: 10.12691/jcsa-8-2-1
Pub. Date: July 22, 2020
4108 Views605 Downloads3 Likes