arXiv subjects

Mike Nkongolo

Publications and source records attributed to Mike Nkongolo.

15 recordsLinked to original sources

arXiv2025

Cybersecurity policy adoption in South Africa: Does public trust matter?

This study examines how public perception influences the implementation and adoption of cybersecurity frameworks in South Africa. Using the PRISMA methodology, a systematic literature review was conducted across reputable scholarly databases, yielding 34 relevant sources aligned with predefined inclusion criteria. Cybersecurity, governance, trust, privacy, cybercrime, and public opinion emerged as dominant thematic clusters. Bibliometric and thematic analyses, supported by network visualisations, revealed that while trust and public sentiment affect cybersecurity policy adoption globally, these factors have minimal influence within the South African policy landscape, despite the country's high cybercrime prevalence. In response, the study proposes a trust-centric policymaking framework designed to integrate public perception as a proactive dimension of cybersecurity governance. This framework seeks to prevent trust deficits from obstructing policy effectiveness and provides guidance for restoring trust where it has eroded.

cs.CR↗

arXiv2025

TriLex: A Framework for Multilingual Sentiment Analysis in Low-Resource South African Languages

Low-resource African languages remain underrepresented in sentiment analysis, limiting both lexical coverage and the performance of multilingual Natural Language Processing (NLP) systems. This study proposes TriLex, a three-stage retrieval augmented framework that unifies corpus-based extraction, cross lingual mapping, and retrieval augmented generation (RAG) driven lexical refinement to systematically expand sentiment lexicons for low-resource languages. Using the enriched lexicon, the performance of two prominent African pretrained language models (AfroXLMR and AfriBERTa) is evaluated across multiple case studies. Results demonstrate that AfroXLMR delivers superior performance, achieving F1-scores above 80% for isiXhosa and isiZulu and exhibiting strong cross-lingual stability. Although AfriBERTa lacks pre-training on these target languages, it still achieves reliable F1-scores around 64%, validating its utility in computationally constrained settings. Both models outperform traditional machine learning baselines, and ensemble analyses further enhance precision and robustness. The findings establish TriLex as a scalable and effective framework for multilingual sentiment lexicon expansion and sentiment modeling in low-resource South African languages.

cs.CL↗

arXiv2024

Ransomware detection using stacked autoencoder for feature selection

The aim of this study is to propose and evaluate an advanced ransomware detection and classification method that combines a Stacked Autoencoder (SAE) for precise feature selection with a Long Short Term Memory (LSTM) classifier to enhance ransomware stratification accuracy. The proposed approach involves thorough pre processing of the UGRansome dataset and training an unsupervised SAE for optimal feature selection or fine tuning via supervised learning to elevate the LSTM model's classification capabilities. The study meticulously analyzes the autoencoder's learned weights and activations to identify essential features for distinguishing ransomware families from other malware and creates a streamlined feature set for precise classification. Extensive experiments, including up to 400 epochs and varying learning rates, are conducted to optimize the model's performance. The results demonstrate the outstanding performance of the SAE-LSTM model across all ransomware families, boasting high precision, recall, and F1 score values that underscore its robust classification capabilities. Furthermore, balanced average scores affirm the proposed model's ability to generalize effectively across various malware types. The proposed model achieves an exceptional 99% accuracy in ransomware classification, surpassing the Extreme Gradient Boosting (XGBoost) algorithm primarily due to its effective SAE feature selection mechanism. The model also demonstrates outstanding performance in identifying signature attacks, achieving a 98% accuracy rate.

cs.LG↗

arXiv2024

Ransomware Detection Dynamics: Insights and Implications

The rise of ransomware attacks has necessitated the development of effective strategies for identifying and mitigating these threats. This research investigates the utilization of a feature selection algorithm for distinguishing ransomware-related and benign transactions in both Bitcoin (BTC) and United States Dollar (USD). Leveraging the UGRansome dataset, a comprehensive repository of ransomware related BTC and USD transactions, we propose a set of novel features designed to capture the distinct characteristics of ransomware activity within the cryptocurrency ecosystem. These features encompass transaction metadata, ransom analysis, and behavioral patterns, offering a multifaceted view of ransomware-related financial transactions. Through rigorous experimentation and evaluation, we demonstrate the effectiveness of our feature set in accurately extracting BTC and USD transactions, thereby aiding in the early detection and prevention of ransomware-related financial flows. We introduce a Ransomware Feature Selection Algorithm (RFSA) based on Gini Impurity and Mutual Information (MI) for selecting crucial ransomware features from the UGRansome dataset. Insights from the visualization highlight the potential of Gini Impurity and MI-based feature selection to enhance ransomware detection systems by effectively discriminating between ransomware classes. The analysis reveals that approximately 68% of ransomware incidents involve BTC transactions within the range of 1.46 to 2.56, with an average of 2.01 BTC transactions per attack. The findings emphasize the dynamic and adaptable nature of ransomware demands, suggesting that there is no fixed amount for specific cyberattacks, highlighting the evolving landscape of ransomware threats.

cs.CR↗

arXiv2024

Data protection psychology using game theory

The research aims to explore how individuals perceive and interact with data protection practices in an era of increasing reliance on technology and the widespread availability of personal data. The study employs a game theoretical approach to investigate the psychological factors that influence individuals' awareness and comprehension of data protection measures. This involves using strategies, moves, rewards, and observations within the game to gain comprehensive insights into these psychological factors. Through the analysis of player strategies and moves within the game, the research identifies several psychological factors that impact awareness of data protection. These factors include levels of knowledge, attitudes, perceived risks, and individual differences among participants. The findings highlight the intricate nature of human cognition and behavior concerning data protection, offering insights crucial for developing effective awareness games and educational initiatives in this domain.

cs.HC↗

arXiv2023

Stacking an autoencoder for feature selection of zero-day threats

Zero-day attack detection plays a critical role in mitigating risks, protecting assets, and staying ahead in the evolving threat landscape. This study explores the application of stacked autoencoder (SAE), a type of artificial neural network, for feature selection and zero-day threat classification using a Long Short-Term Memory (LSTM) scheme. The process involves preprocessing the UGRansome dataset and training an unsupervised SAE for feature extraction. Finetuning with supervised learning is then performed to enhance the discriminative capabilities of this model. The learned weights and activations of the autoencoder are analyzed to identify the most important features for discriminating between zero-day threats and normal system behavior. These selected features form a reduced feature set that enables accurate classification. The results indicate that the SAE-LSTM performs well across all three attack categories by showcasing high precision, recall, and F1 score values, emphasizing the model's strong predictive capabilities in identifying various types of zero-day attacks. Additionally, the balanced average scores of the SAE-LSTM suggest that the model generalizes effectively and consistently across different attack categories.

cs.CR↗

arXiv2023

Assessing Cyclostationary Malware Detection via Feature Selection and Classification

Cyclostationarity involves periodic statistical variations in signals and processes, commonly used in signal analysis and network security. In the context of attacks, cyclostationarity helps detect malicious behaviors within network traffic, such as traffic patterns in Distributed Denial of Service (DDoS) attacks or hidden communication channels in malware. This approach enhances security by identifying abnormal patterns and informing Network Intrusion Detection Systems (NIDSs) to recognize potential attacks, enhancing protection against both known and novel threats. This research focuses on identifying cyclostationary malware behavior and its detection. The main goal is to pinpoint essential cyclostationary features used in NIDSs. These features are extracted using algorithms such as Boruta and Principal Component Analysis (PCA), and then categorized to find the most significant cyclostationary patterns. The aim of this article is to reveal periodically changing malware behaviors through cyclostationarity. The study highlights the importance of spotting cyclostationary malware in NIDSs by using established datasets like KDD99, NSL-KDD, and the UGRansome dataset. The UGRansome dataset is designed for anomaly detection research and includes both normal and abnormal network threat categories of zero-day attacks. A comparison is made using the Random Forest (RF) and Support Vector Machine (SVM) algorithms, while also evaluating the effectiveness of Boruta and PCA. The findings show that PCA is more promising than using Boruta alone for extracting cyclostationary network feature patterns. Additionally, the analysis identifies the internet protocol as the most noticeable cyclostationary feature pattern used by malware. Notably, the UGRansome dataset outperforms the KDD99 and NSL-KDD, achieving 99% accuracy in signature malware detection using the RF algorithm and 98% with the SVM.

cs.CR↗

arXiv2023

Navigating the complex nexus: cybersecurity in political landscapes

Cybersecurity in politics has emerged as a critical and intricate realm intersecting technology, governance, and international relations. In this interconnected digital context, political entities confront unparalleled challenges in securing sensitive data, upholding democratic procedures, and countering cyber threats. This study delves into the multifaceted landscape of political cybersecurity, examining the evolving landscape of cyberattacks, their impact on political stability, and strategies for bolstering digital resilience. The intricate interplay between state-sponsored hacking, disinformation campaigns, and eroding public trust underscores the imperative for robust cybersecurity measures to safeguard political system integrity. Through an extensive exploration of real-world case studies, policy frameworks, and collaborative initiatives, this research illuminates the intricate network of technological vulnerabilities, geopolitical dynamics, and ethical concerns that shape the dynamic evolution of cybersecurity in politics. Amidst evolving digital landscapes, the imperative for agile and preemptive cybersecurity strategies is paramount for upholding the stability and credibility of political institutions.

cs.CY↗

arXiv2023

Software-based signal compression algorithm for ROM-stored electrical cables

This project introduces a groundbreaking approach to address the challenge of periodic signal compression. By proposing a novel adaptive coding method, coupled with hardware-assisted data compression, we have developed a new architecture model tailored for efficient data compression. The selected compression scheme has demonstrated remarkable results, showcasing reduced memory communication volume and power consumption in the cache memory path of benchmark systems. With a reduction range of 4.2% to 35.2%, this innovation paves the way for affordable smart sensing, monitoring, diagnostics, and protection in emerging low-cost device types. Consequently, this cutting-edge technology enhances electrical signal compression and contributes to grid improvement. Additionally, we explore the novel application of harnessing wasted thermal energy in the Read-Only Memory (ROM) using thermoelectricity (TE). This approach captures the excess thermal energy, converting it into electrical energy through optimized supercapacitor charging, resulting in efficient energy utilization. This innovation intersects the fields of embedded systems, data compression, energy efficiency, and smart grid technology.

cs.IT↗

arXiv2023

Fuzzification-based Feature Selection for Enhanced Website Content Encryption

We propose a novel approach that utilizes fuzzification theory to perform feature selection on website content for encryption purposes. Our objective is to identify and select the most relevant features from the website by harnessing the principles of fuzzy logic. Fuzzification allows us to transform the crisp website content into fuzzy representations, enabling a more nuanced analysis of their characteristics. By considering the degree of membership of each feature in different fuzzy categories, we can evaluate their importance and relevance for encryption. This approach enables us to prioritize and focus on the features that exhibit higher membership degrees, indicating their significance in the encryption process. By employing fuzzification-based feature selection, we aim to enhance the effectiveness and efficiency of website content encryption, ultimately improving the overall internet security.

cs.CR↗

arXiv2023

Fuzzy Feature Selection with Key-based Cryptographic Transformations

In the field of cryptography, the selection of relevant features plays a crucial role in enhancing the security and efficiency of cryptographic algorithms. This paper presents a novel approach of applying fuzzy feature selection to key-based cryptographic transformations. The proposed fuzzy feature selection leverages the power of fuzzy logic to identify and select optimal subsets of features that contribute most effectively to the cryptographic transformation process. By incorporating fuzzy feature selection into key-based cryptographic transformations, this research aims to improve the resistance against attacks and enhance the overall performance of cryptographic systems. Experimental evaluations may demonstrate the effectiveness of the proposed approach in selecting secure key features with minimal computational overhead. This paper highlights the potential of fuzzy feature selection as a valuable tool in the design and optimization of key-based cryptographic algorithms, contributing to the advancement of secure information exchange and communication in various domains.

cs.CR↗

arXiv2023

Data Protection for Data Privacy-A South African Problem?

This study proposes a comprehensive framework for enhancing data security and privacy within organizations through data protection awareness. It employs a quantitative method and survey research strategy to assess the level of data protection awareness among employees of a public organization.

cs.CR↗

arXiv2023

Cybersecurity Career Requirements: A Literature Review

This study employs a systematic literature review approach to identify the requirements of a career as a cybersecurity professional. It aims to raise public awareness regarding opportunities in the Information Security (IS) profession. A total of 1,520 articles were identified from four academic databases by searching using the terms "cybersecurity" and "skills". After rigorous screening according to various criteria, 31 papers remained. The findings of these studies were thematically analyzed to describe the knowledge and skills an IS professional should possess. The research found that a considerable investment in time is necessary for cybersecurity professionals to reach the required technical proficiency. It also identified female gender barriers to cybersecurity careers due to the unique requirements of the field and suggests that females may successfully enter at lower levels and progress up the tiers as circumstances dictate.

cs.CY↗

arXiv2023

Smart Sentiment Analysis-based Search Engine Classification Intelligence

Search engines are widely used for finding information on the internet. However, there are limitations in the current search approach, such as providing popular but not necessarily relevant results. This research addresses the issue of polysemy in search results by implementing a search function that determines the sentimentality of the retrieved information. The study utilizes a web crawler to collect data from the British Broadcasting Corporation (BBC) news site, and the sentimentality of the news articles is determined using the Sentistrength program. The results demonstrate that the proposed search function improves recall value while accurately retrieving nonpolysemous news. Furthermore, Sentistrength outperforms deep learning and clustering methods in classifying search results. The methodology presented in this article can be applied to analyze the sentimentality and reputation of entities on the internet.

cs.IR↗

arXiv2023

Zero-Day Threats Detection for Critical Infrastructures

Technological advancements in various industries, such as network intelligence, vehicle networks, e-commerce, the Internet of Things (IoT), ubiquitous computing, and cloud-based applications, have led to an exponential increase in the volume of information flowing through critical systems. As a result, protecting critical infrastructures from intrusions and security threats have become a paramount concern in the field of intrusion detection systems (IDS). To address this concern, this research paper focuses on the importance of defending critical infrastructures against intrusions and security threats. It proposes a computational framework that incorporates feature selection through fuzzification. The effectiveness and performance of the proposed framework is evaluated using the NSL-KDD and UGRansome datasets in combination with selected machine learning (ML) models. The findings of the study highlight the effectiveness of fuzzy logic and the use of ensemble learning to enhance the performance of ML models. The research identifies Random Forest (RF) and Extreme Gradient Boosting (XGB) as the top performing algorithms to detect zero-day attacks. The results obtained from the implemented computational framework outperform previous methods documented in the IDS literature, reaffirming the significance of safeguarding critical infrastructures from intrusions and security threats.

cs.CR↗