Browsing by Author "Ngubiri, John"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Improvement of Malware Classification Using Hybrid Feature Engineering
    (SN Computer Science, 2020) Masabo, Emmanuel; Kaawaase, Kyanda Swaib; Sansa‑Otim, Julianne; Ngubiri, John; Hanyurwimfura, Damien
    Polymorphic malware has evolved as a major threat in Computer Systems. Their creation technology is constantly evolving using sophisticated tactics to create multiple instances of the existing ones. Current solutions are not yet able to sufficiently address this problem. They are mostly signature based; however, a changing malware means a changing signature. They, therefore, easily evade detection. Classifying them into their respective families is also hard, thus making elimination harder. In this paper, we propose a new feature engineering (NFE) approach for a better classification of polymorphic malware based on a hybrid of structural and behavioural features. We use accuracy, recall, precision, and F score to evaluate our approach. We achieve an improvement of 12% on accuracy between raw features and NFE features. We also demonstrated the robustness of NFE on feature selection as compared to other feature selection techniques.
  • Thumbnail Image
    Item
    Performance of the Energy Aware Routing Protocol in Wireless Sensor Networks with mobile nodes
    (International Conference on Wireless Networks (ICWN), 2012) Fote Kamanyi, Antonia; Ngubiri, John; Sansa-Otim, Julianne
    Wireless Sensor Networks (WSNs) are increasing in popularity. This is due to several applications (like car tracking, acute patient monitoring and forest fire detection). Energy in WSNs is a scarce resource and therefore has to be optimized. Several studies on energy aware routing schemes have been made. However, most of them cater for fixed nodes yet in some cases, some WSN nodes are mobile. In this paper, we extend the Energy Aware Routing Protocol (EARP) [1] to cater for WSNs with some mobile nodes. We propose EARP with Mobility Support (EARP-MS) and evaluate its performance. We show that (i) the energy consumed increases as the distance between the source and recipient nodes increase, (ii) providing for node mobility prolongs the WSN lifespan, (iii) mobile nodes have higher residual energy than the static nodes and (iv) the average transmission time is lower when some nodes are mobile..
  • Thumbnail Image
    Item
    A State of the Art Survey on Polymorphic Malware Analysis and Detection Techniques
    (Journal of Soft Computing, 2018) Masabo, Emmanuel; Kaawaase, Kyanda Swaib; Sansa-Otim, Julianne; Ngubiri, John; Hanyurwimfura, Damien
    Nowadays, systems are under serious security threats caused by malicious software, commonly known as malware. Such malwares are sophisticatedly created with advanced techniques that make them hard to analyse and detect, thus causing a lot of damages. Polymorphism is one of the advanced techniques by which malware change their identity on each time they attack. This paper presents a detailed systematic and critical review that explores the available literature, and outlines the research efforts that have been made in relation to polymorphic malware analysis and their detection.