Natural Language Processing with machine learning for anomaly detection on system call logs
- Authors: Goosen, Christo
- Date: 2023-10-13
- Subjects: Natural language processing (Computer science) , Machine learning , Information security , Anomaly detection (Computer security) , Host-based intrusion detection system
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/424699 , vital:72176
- Description: Host intrusion detection systems and machine learning have been studied for many years especially on datasets like KDD99. Current research and systems are focused on low training and processing complex problems such as system call returns, which lack the system call arguments and potential traces of exploits run against a system. With respect to malware and vulnerabilities, signatures are relied upon, and the potential for natural language processing of the resulting logs and system call traces needs further experimentation. This research looks at unstructured raw system call traces from x86_64 bit GNU Linux operating systems with natural language processing and supervised and unsupervised machine learning techniques to identify current and unseen threats. The research explores whether these tools are within the skill set of information security professionals, or require data science professionals. The research makes use of an academic and modern system call dataset from Leipzig University and applies two machine learning models based on decision trees. Random Forest as the supervised algorithm is compared to the unsupervised Isolation Forest algorithm for this research, with each experiment repeated after hyper-parameter tuning. The research finds conclusive evidence that the Isolation Forest Tree algorithm is effective, when paired with a Principal Component Analysis, in identifying anomalies in the modern Leipzig Intrusion Detection Data Set (LID-DS) dataset combined with samples of executed malware from the Virus Total Academic dataset. The base or default model parameters produce sub-optimal results, whereas using a hyper-parameter tuning technique increases the accuracy to within promising levels for anomaly and potential zero day detection. , Thesis (MSc) -- Faculty of Science, Computer Science, 2023
- Full Text:
Social Learning and Regenerative Sustainability: Unlocking value created in sustainability projects in higher education
- Authors: Royle, Carlene
- Date: 2023-10-13
- Subjects: Social Learning South Africa Makhanda , Sustainability South Africa Makhanda , Education, Higher Social aspects South Africa Makhanda , Social accounting South Africa Makhanda , Education, Higher Activity programs South Africa Makhanda , Value creation , Agent (Philosophy) , Sustainable Development Goals
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/402981 , vital:69911
- Description: This qualitative study considers two bodies of theory, regenerative sustainability and social learning theory, within a tertiary education context. Universities offer unique opportunities, across both the formal and informal curriculum, that engage with the two-fold socioeconomic and environmental crises. The study explores both the promise of unlocking value in an ex-linear economy; and the healing and regenerative benefits in moving toward greener practices. Through an embedded case study at Rhodes University, in the Eastern Cape of South Africa, this research explores the value that is being unlocked in campus-based sustainability projects, when considered through a social learning lens (Lave and Wenger, 1991). Invitations to participate in this study were extended to project-leads of sustainability initiatives originating from Rhodes University campus. Six projects, which have been active on campus in recent years, were selected and, through semi-structured interviews, the insights of 12 participants were captured and analysed using the associated Value Creation Framework (VCF) developed by Wenger, Trayner and De Laat (Wenger, Trayner, de Laat, 2011) and later Wenger-Trayner and Wenger Trayner (2014, 2015, 2020). The VCF consists of value cycles that interconnect dynamically, including Orientating, Strategic, Enabling, Immediate, Potential, Applied, Realised and Reframed or Transformative value cycles. The study identified instances of all these value cycles, within and across the six embedded case studies (project). Drawing on social learning theorists the analysis further focused on instances of collaboration, agency and boundary crossing. Additional themes that emerged across the majority of the embedded study projects, were a convergence of socio and eco; a whole-systems perspective shared by project leads; the importance of the social commons; language as an enabler; and problem solving for system change. A recommendation is proposed to further unlock the unbounded value created through such projects by reframing the informal curriculum opportunities offered on university campuses as social learning spaces where students can practice agency. To do so, would require formalizing various forms of system support, thus facilitating expanded learning in regenerative sustainability activities, for the common social and planetary good. , Thesis (MEd) -- Faculty of Education, Education, 2023
- Full Text:
The mathematical and pedagogical content knowledge that Namibian senior primary teachers draw on to develop their learners’ computational estimation
- Authors: Shigwedha, Emilia Ndilimeke
- Date: 2023-10-13
- Subjects: Uncatalogued
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/424108 , vital:72124
- Description: Computational estimation is important in the development of learners’ number sense. It is through the process of finding an approximate (but satisfactory) that learners can check the reasonableness of their answers to calculations, develop an understanding of place value and by implication the four number operations. It is the role of teachers to develop the computational estimation skills of learners. To do this, teachers need to have a sound knowledge of computational estimation, its value and how to teach it. This study thus seeks to explore and understand Namibian senior primary teachers’ mathematical and pedagogical content knowledge to develop their learners’ computation estimation knowledge. The research is guided by the following question: What mathematical and pedagogical content knowledge do senior primary mathematics teachers draw on to develop their learners’ computational estimation skills? The research is a qualitative interpretivist case study. Eight senior primary teachers of Mathematics from the Ohangwena region in Namibia participated in the study. Data was generated through questionnaires, a focus group interview and lesson observations. The Mathematics Knowledge for Teaching (Ball et al., 2008) and the Knowledge Quartet (Rowland, 2005) frameworks were used as both analytic and explanatory tools for the study. Key findings from the research are that teachers have knowledge of and use a variety of strategies for estimation, however, they only use the ‘rounding off’ strategy when teaching learners computational estimation. The teachers appear to teach computational estimation by first focusing on place value before moving on to ‘rounding off’ to the nearest 10s, 100s, 1000s and so forth. My research recommends that the National Institute of Educational Development together with the Ministry of Education, Art and Culture in Namibia, provide teachers with professional development opportunities on how to develop learners’ computational estimation. Such professional development will further develop teachers’ mathematical and pedagogical content knowledge. Furthermore, the Namibian syllabus should include a variety of strategies for computational estimation. , Thesis (MEd) -- Faculty of Education, Primary and Early Childhood Education, 2023
- Full Text:
The potential of social learning to upscale the Community Based Water Quality Management (CBWQM) process: A case study of the Mpophomeni and Baynespruit Enviro Champs project
- Authors: Sithole, Nkosingithandile
- Date: 2023-10-13
- Subjects: Community of practice , Social learning , Water quality management South Africa Pietermaritzburg Citizen participation , Citizen science , Water quality South Africa Pietermaritzburg
- Language: English
- Type: Academic theses , Master's theses , text
- Identifier: http://hdl.handle.net/10962/402966 , vital:69910
- Description: Water is an essential component of human survival, with a wide variety of uses such as washing, cooking, drinking and growing food. Covering approximately 70% of the Earth’s surface, water is necessary for all human survival, and is a source of life for plants and animals. Only 0.036% of freshwater can be accessed and utilised by humans, which is not enough to support the rapidly growing population and economic development. This water is further exhausted by pollution caused by sewage leaks, littering, agricultural runoff and industry discharge which deteriorate water quality significantly. To exacerbate these water issues, the major issue of water accessibility is not directly linked to quantity but has been primarily attributed to poor water governance, at a global and local level (in South Africa). Poorly maintained water infrastructure and inadequate cooperative governance have resulted in the establishment of many Community Based Water Quality Management (CBWQM) projects in South Africa, to respond to water quality monitoring and management challenges. The aim of this study was firstly, to investigate how social learning was occurring within two CBWQM Communities of Practice (CoPs) located in KwaZulu-Natal, Pietermaritzburg, namely, the Baynespruit and the Mpophomeni Enviro Champs project (Case Study 1 and 2 respectively), and the potential of social learning to upscale CBWQM. Additionally, it sought to identify the type of support required for the scaling of social learning outcomes in CBWQM communities of practice, along two potential scaling pathways that were identified in a national study on scaling of CBWQM: Scaling Pathway 1(Policy engagement and support) and Scaling Pathway 2 (Capacity building). The research was undertaken as a qualitative case study approach, with data collected through semi-structured interviews, document, and questionnaire analysis to investigate social learning within the two selected case studies. The data was coded and indexed using a thematic analysis technique and an analytical framework as a tool to investigate how social learning was occurring in both case studies and explore the potential required to upscale it. The study found that there is an existing gap between policy and practice with regard to CBWQM support by government structures. Despite South African water policy advocating for public participation in water resource management, there has been limited support from government to support and resource CBWQM projects over a long period of time. To upscale the practice of CBWQM, the study found that capacity building and learning needs to be improved and better supported practically through models such as the 5Ts of learning, and through supporting CBWQM participants’ learning journey to establish learning pathways for them. , Thesis (MEd) -- Faculty of Education, Education, 2023
- Full Text: