Conferences / Workshops / Seminars +

Permanent URI for this community

http://hdl.handle.net/11071/3874

Browse

Browsing Conferences / Workshops / Seminars + by Author "Abeka, Silvance"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Enhanced information security model using an integrated approach
    (Strathmore University, 2019-08) Sirma, Jerotich; Abeka, Silvance; Raburu, George; Okelo, Benard
    Organizational assets are mainly vulnerable to attacks from user error, hackers and crackers, viruses and cyber criminals. This has resulted in loss of trillions of dollars around the world and over 4 billion shillings in East Africa. The objective of the study is to develop an enhanced information security model using an integrated approach among SACCOS in Kenya and to test and validate the enhanced information security model. The study used descriptive research. The total population of the study comprised of 135 SACCOS. Nassiuma (2000) scientific formula was used to determine the sample size of 85 SACCOS registered with SASRA. A pilot study was carried out to test the validity of the survey instrument. Cronbachs alpha of 0.70 coefficient variation was used to assess the internal reliability of the research instrument. The results of the study revealed that the enhanced information security model is suitable to enhance the information security within the SACCOS sector. This is evident because the findings indicated that the elements of risk assessment have positive significant effect on the enhanced information security among SACCOS. Important contributions to the body of knowledge were the development of an enhanced information security model using an integrated approach for SACCOS in Kenya.
  • Thumbnail Image
    Item
    Machine learning algorithm for advanced persistent threat detection
    (Strathmore University, 2019-08) Omollo, Vincent; Abeka, Silvance
    Networked computer syster:ns are increasingly being employed to run critical infrastructural activities by both private companies and governments. Advanced persistent threats have emerged as serious security threats to these networks due to their level of sophistication and multiple attack vectors. Conventional countermeasures against these network threats have been antivirus, antimalware, firewalls, intrusion detection systems, intrusion prevention systems and sandboxing. However, these techniques are ineffective against advanced persistent threats since the attackers employ a number of evasion techniques such as code obfuscation and encryption. In addition, these technologies are rarely monitored or updated, hence lulling end-user enterprises into a false sense of security. The signature based scanning utilized in some of these technologies is unable of detecting new and sophisticated malware. Sandboxes on their part, a number of malware deploy sandbox detection techniques that help them detect when they are being analyzed and evade the sandbox by hiding their malicious behavior. Due to these shortfalls, researchers have proposed machine learning, deep neural networks, and data mining using misuse detection and anomaly detection as possible threat detection strategies. Unfortunately, machine learning and deep neural networks are susceptible to evasion attacks using adversarial examples that involve small changes to the input data that cause misclassification at test time. Misuse detection is unable to discover attacks whose instances have not yet been observed while anomaly detection can generate false positives due to previously unseen and yet legitimate system behaviors being recognized as anomalies, and hence flagged as potential intrusions. The aim of this paper will be therefore to implement an enhanced algorithm for intrusion detection using machine learning to curb the rising number of advanced persistent threats.