Browsing by Author "Kamau, John"

Now showing 1 - 3 of 3
  • Thumbnail Image
    PublicationOpen Access
    A Review of Users Adoption of Open Source Software in Africa
    (Canadian Center of Science and Education, 2012) Kamau, John; Namuye, Sylvester
    In the current world, software is increasingly becoming important in the human activity. It is widely recognised that Open Source software (OSS) is freely available to anyone who needs it. However, loyalty of computer users to proprietary operating systems and general office applications seems to be still high especially in developing countries. OSS has a great potential of saving costs for developing economies in Africa and reducing the cost of doing business and automating operations. The software would be very useful especially in the current period of economic hardships being faced by many developing countries. African governments have also not taken the lead in adopting the OSS software and many do not have policies in place regarding it. A review of literature on studies conducted in Africa on OSS in order to establish the level of user adoption, possible barriers to OSS adoption in developing countries in Africa is done in this paper. The findings are of great value to all stakeholders, namely the software developers, policy makers and computer experts in their endeavour to achieve high user adoption of OSS.
  • No Thumbnail Available
    PublicationOpen Access
    Sentence Level Analysis Model for Phishing Detection
    (Journal of cyber security, 2023-09-11) Gikandi, Joyce; Njuguna, David; Kamau, John; Sawe, Lindah
    Phishing emails have experienced a rapid surge in cyber threats globally, especially following the emergence of the COVID-19 pandemic. This form of attack has led to substantial financial losses for numerous organizations. Although various models have been constructed to differentiate legitimate emails from phishing attempts, attackers continuously employ novel strategies to manipulate their targets into falling victim to their schemes. This form of attack has led to substantial financial losses for numerous organizations. While efforts are ongoing to create phishing detection models, their current level of accuracy and speed in identifying phishing emails is less than satisfactory. Additionally, there has been a concerning rise in the frequency of phished emails recently. Consequently, there is a pressing need for more efficient and high-performing phishing detection models to mitigate the adverse impact of such fraudulent messages. In the context of this research, a comprehensive analysis is conducted on both components of an email message – namely, the email header and body. Sentence-level characteristics are extracted and leveraged in the construction of a new phishing detection model. This model utilizes K Nearest Neighbor (KNN)introducing the novel dimension of sentence-level analysis. Established datasets from Kaggle was employed to train and validate the model. The evaluation of this model’s effectiveness relies on key performance metrics including accuracy of 0.97, precision, recall, and F1-measure.
  • Thumbnail Image
    PublicationOpen Access
    Sentence Level Analysis Model for Phishing Detection Using KNN
    (Journal of cyber security, 2024-01-11) Sawe, Lindah; Njuguna, David; Kamau, John; Gikandi, Joyce
    Phishing emails have experienced a rapid surge in cyber threats globally, especially following the emergence of the COVID-19 pandemic. This form of attack has led to substantial financial losses for numerous organizations. Although various models have been constructed to differentiate legitimate emails from phishing attempts, attackers continuously employ novel strategies to manipulate their targets into falling victim to their schemes. This form of attack has led to substantial financial losses for numerous organizations. While efforts are ongoing to create phishing detection models, their current level of accuracy and speed in identifying phishing emails is less than satisfactory. Additionally, there has been a concerning rise in the frequency of phished emails recently. Consequently, there is a pressing need for more efficient and high-performing phishing detection models to mitigate the adverse impact of such fraudulent messages. In the context of this research, a comprehensive analysis is conducted on both components of an email message—namely, the email header and body. Sentence-level characteristics are extracted and leveraged in the construction of a new phishing detection model. This model utilizes K Nearest Neighbor (KNN) introducing the novel dimension of sentence-level analysis. Established datasets from Kaggle were employed to train and validate the model. The evaluation of this model’s effectiveness relies on key performance metrics including accuracy of 0.97, precision, recall, and F1-measure.