Theses supervised by Dr. Öğr. Üyesi Muhammad Ilyas
12 theses · Altınbaş University
Ai-based optimization of blockchain protocols for cybersecurity in iot systems in medium-sized organizations
The Internet of Things (IoT) has enabled small and medium enterprises (SMEs) to automate and make their operations more efficient. Unfortunately, the need to keep these facilities online exposes them to cybersecurity threats that can wreak havoc on their reliability and integrity. The object of this study is to fill this gap by assessing AI-driven optimizations and their effects on real-time threat detection and response. Data regarding enterprise IoT utilization and customers' behavior were collected and analyzed using statistical methods such as percentage distributions, normality tests, linear regression, analysis of variance (ANOVA), etc. The improved outcomes in cybersecurity of AI-enhanced blockchain protocols were validated using the Amazon IoT dataset, yielding a relative coefficient R² of 0.947. AI also played a sig. positive role in real-time threat detection and mitigation, backed by p-values (<0.05) and statistical sig. (>2). These results place emphasis on the continuous training of AI models and regular updates of blockchain protocols as mandatory for the sustainability of the system, resilience, and ability to withstand multi-pronged and persistent threats.
Sağlık IoT cihazlarının güvenliğinin sağlanması ve SIEM entegrasyonunun sağlanması: aAdresleme
This thesis explores the growing use of Internet of Things (IoT) devices in healthcare, which has transformed patient care with advanced monitoring and treatment options. However, this integration poses security challenges, demanding robust protective measures. The study focuses on integrating Security Information and Event Management (SIEM) systems with healthcare IoT devices as a solution. Through a thorough literature review, it sheds light on the current state of IoT security, emphasizing the need for improved protective measures. The main issue addressed is the vulnerability of healthcare IoT devices to security breaches and the associated risks to patient data and device functionality. To address this, the research suggests a comprehensive security framework tailored for these devices. This framework, drawn from literature and best practices, includes crucial security measures such as authentication, data encryption, access controls, and anomaly detection. Integrating SIEM systems into this framework provides real-time threat detection and swift incident response, bolstering the overall security of healthcare IoT devices. The thesis highlights the importance of this integration, offering a roadmap for secure, efficient, and effective implementations of healthcare IoT
Retinal eye disease detection using deep learning
The global prevalence of retinal abnormalities affects millions of individuals, highlighting the urgency of early detection and intervention to prevent the advancement of these conditions, ultimately mitigating the risk of avoidable blindness. In this thesis, we delve into the critical realm of retinal disease detection using deep learning techniques. Leveraging a diverse ensemble of state-of-the-art neural network architectures, including MobileNetV2, ResNet50, InceptionV3, and DenseNet, we conduct a comprehensive evaluation of their performance in classifying retinal scans. Our meticulous preprocessing steps, resize images, convert grayscale to RGB and rigorous training cycles lay the foundation for an advanced model. Notably, our results reveal that ResNet50 outperforms other models, achieving an accuracy of 0.89, setting a new benchmark in retinal scan analysis. This research contributes to the vital field of early retinal disease detection, offering the potential to enhance clinical diagnosis and patient outcomes
Integrate lightweight cryptography and monitoring framework for secure and efficient IoT-Enabled cloud system
In the present generation, security issues are a major issue experienced by everyone due to the increase in digital technologies. With the introduction of digital technologies, data is stored and transmitted through platforms where security issues arise. Many cryptographic techniques are available to protect data in transmission and storage through digital technologies to overcome security issues. The methods are utilized to encrypt the data with passwords or PIN codes, which hackers can easily identify. In this case, for a safe process, a hybrid encryption method is proposed in this thesis for security data purposes, integrated with lightweight and hidden ciphertext policy attributes with the assistance of the cloud IoT environment. The lightweight encryption provides proxy services for data authentication. The analysis of the security has provided a positive impact on the encryption of the integrated lightweight. The system offers better positive results with hybrid encryption for data authentication for security purposes. The third part of the framework introduces a hybrid encryption system that combines a hidden hierarchical policy with a lightweight Ciphertext Policy Attribute-Based Encryption (CP-ABE) enforcement model. This is to ensure fine grained access control, minimal computational burden, and efficient encryption-decryption suited for IoT devices. It also incorporates QGE-HMAC for secure message authentication and ELP-DSA for signature validation, providing strong protection for encryption key integrity and end-to-end data authenticity. The final part presents a reliable cloud-enabled IoT network monitoring system powered by JPAO-GRU. This advanced gated recurrent unit model integrates Aranda-Ordaz activation and Jeffreys prior regularization for accurate anomaly detection. Additionally, the framework includes HTT-Fuzzy logic for outdated device detection, QASOA for intelligent load balancing, and LCA-BST for low-latency, Hierarchical device monitoring. Comprehensive experimental validation shows that the The proposed dual approach enhances security, integrity, and network efficiency, achieving high accuracy (99.12%) in intrusion detection, 99.18% encryption security, and substantial reductions in encryption time, latency, and energy consumption. This research contributes a A unified and scalable solution for addressing the growing security, authentication, and trust challenges in next-generation cloud-IoT systems.
Spss yöntemlerinin enerji sistemleri ve endüstriyel kontrol sistemlerindeki siber güvenlik risklerinin analizinde uygulanması
Cyberattacks can significantly undermine public confidence in organizations, disrupt financial operations, and result in significant financial losses. The purpose of this research paper is to explore the relationship between ROA, efficiency in operations, and cybersecurity through descriptive and inferential statistics. The study was conducted in two rounds at various locations mainly at the significant commercial and industrial hubs of Libya. The initial phase had been conducted, where 58% of respondents were aged between 25 and 35 years, while 24% were aged below 25, and 18% were older than 35 years. During the second phase, a significantly greater proportion of participants (84.3%) were under 25 by 9%; and, correspondingly, only 6.7% of participants were over age 35. The correlation analysis showed a strong positive association between profitability, operational efficiency and cybersecurity in both periods. In the first phase, profitability was positively related to both operational efficiency (r = 0.806) and cybersecurity (r = 0.657), and all correlations were statistically significant (p < 0.01). Similarly, the second phase also showed strong positive correlations with profitability, operational efficiency (r = 0.862), and cybersecurity (r = 0.732), confirming the robustness of these relationships over time.
Makine öğrenimi kullanarak DDOS saldırısı algılaması için trafik sınıflandırması
Anomaly detection remains a major concern for many Internet players. It is a complex problem, having attracted the interest of both industrial players, such as Internet Service Providers (ISPs), and members of the scientific community. These anomalies, defined as events deviating from the usual behaviour of traffic, can have severe consequences on the services provided. While some anomalies may be the result of configuration errors, it is scans and attacks that are of most interest to digital players We present our problem here, divided into three parts. First, we cover all the things to consider when building a detector. We then address several challenges related to current traffic. Finally, we discuss the specificity of distributed denial of service attacks Thus, this thesis seeks to propose new solutions, taking into account all the components of this problem. we first present the motivations of project, for which our work was carried out. The problem to which we answer is then exposed. then, we introduce our different contributions to answer this problemWe present our problem here, divided into three parts. First, we cover all the things to consider when building a detector. We then address several challenges related to current traffic. Finally, we discuss the specificity of distributed denial of service attacksThus, this thesis seeks to propose new solutions, taking into account all the components of this problem. we first present the motivations of project, for which our work was carried out. The problem to which we answer is then exposed. then, we introduce our different contributions to answer this problem.
Cybersecurity risk assessment for unmanned aircraft systems
Today, cybersecurity and safety are two of the most pressing operations in UAS development. There has been a lot of work put in by legislators and aviation authorities to ensure that UAS operations inside the existing airspace system are safe. Specific Operation Risk Assessment (SORA) is a methodology developed by the Joint Authorities for Rulemaking on Unmanned Aircraft Systems (JARUS). This methodology may be used as a risk for assessing the assessments associated with Specific Category UAS operations. However, only a subset of safety-related issues may be addressed by the methodology. This document details the steps we took to adapt the SORA methodology for use in the field of cybersecurity. To demonstrate this strategy, we broaden the methodology to include the secrecy challenge On the areas of official government buildings and military and security areas, which is a part of cybersecurity.
Improving vanets systems security against DDOS attacks by using machine-learning algorithm
With the fast and huge vehicular communication systems currently being developed, there is a clear and urgent need for advanced security to determine whether a vehicle has been attacked. Therefore, we developed a tool called the misbehavior detection system (MDS), which is intended to help the vehicle take action and minimize any potential harm from attackers. One of the most dangerous forms of attacks that threaten vehicular communication systems is distributed denial of service (DDoS) attacks. Increasing the security of VANETs against such attacks is a topic that a large number of researchers are now considering, to provide highly effective security capabilities, machine learning (ML) techniques were applied. NSL-KDD or KDD-CUP99 datasets form the basis for the greater part of the current research. Attacks on these datasets were outdated. Therefore, we used a new dataset generated by OMNeT++, Veins, and Sumo. Seven different types of attack densities were conducted during this simulation, and the XGBoost classifier was used to evaluate and predict MDS systems. The median F1-score for this XGBoost classifier was 99.70%, which represented a clear advantage over another ML method, where we used the Synthetic Minority Oversampling Technique (SMOTE) to class balance the datasets.
Kripto sistemleri için kaos teorisini kullanarak bulut bilgisayar güvenliğini artırma
The safety of the information stored in the cloud has emerged as a primary worry in recent years alongside the expansion of cloud computing. Traditional encryption algorithms, such as Advanced Encryption Standard (AES), are susceptible to attacks, particularly when the keys are held on the cloud. This is because cloud providers encrypt data to protect it from unauthorized access. As a consequence of this, there is a requirement for an updated encryption method that offers a higher level of protection for data stored in the cloud. In this thesis, a modified version of the AES algorithm is proposed as a solution to the problem of ensuring the safety of cloud data by improving the key management and encryption procedure. In order to protect the secrecy, integrity, and authenticity of data stored in the cloud, a modified version of the AES algorithm makes use of a hybrid key management technique. This strategy combines the benefits of symmetric and asymmetric encryption. A randomized encryption procedure is also a part of the method. This process helps to ensure that the ciphertext is completely unique and makes it more difficult for adversaries to break the encryption. Using a cloud-based system, the purpose of this paper is to analyze the efficiency as well as the safety of a modified version of the AES algorithm. The evaluation will include a comparison of the modified AES algorithm with typical encryption algorithms, such as AES and RSA, in terms of security, efficiency, and scalability. [CDATA[The evaluation will include a comparison of the modified AES algorithm with traditional encryption algorithms, such as AES and RSA. The findings of the evaluation will illustrate the efficacy of the modified AES algorithm in preventing illegal access to cloud data and preserving the confidentiality and safety of cloud-based systems.
Altı uzay öğrenme tabanlı tek sınıf sınıflandırma kullanılarak optimize edilmiş bir kötü amaçlı yazılım tespit tekniği
Advancement in technology have imposed on security specialists to constantly find new methods and solution to system security problems. Accordingly, Cybersecurity was at the forefront of the solutions that must be researched. The problem here is that the danger exists continuously and has different forms that can be altered, this can camouflage the risk and thus being able to deceive the protection program. Since including the whole set of security problems and trying to find a solution that solves them collectively will be an impossible mission, since the security problems have a wide spectrum and covering them in one shot is impossible. So, taking each problem independently and covering it will be a better solution. Malware is considered as one of the oldest security threats that had widely affected systems, malware variations are numerous, covering the threat of malware will mean covering a good percentage of the security problems, since many of the problems depends on malware to implant its malicious applications inside the system. Three different strategies have been implemented; the goal was to detect malware. The start was with traditional Artificial Intelligence, aiming to test the influence of the header features that exists in the portable executable file on the accuracy of malware detection, two of the three strategies were implemented regarding this issue. The attained results have outperformed other similar implementations. The third strategy that has been implemented was a different novel strategy that has been implemented for the first time. The main aim of this strategy was to overcome all the minor wholes that may lead to obtain a faked good result and this was an important issue. Dataset imbalance and curse of dimensionality were an obstacle that may affect the attained results. This new strategy has bypassed these obstacles and outperformed any previously implemented strategy. The strategy was the subspace learning. The techniques implemented from this strategy were Subspace Support Data Description (SSVDD) and Graph Embedded SSVDD, before implementing them, One-Class Classification and Support Vector Data Description were also tested, results attained from subspace learning have outperformed other results from other techniques implemented previously.
Giyilebilir uygulamalar için meta malzemeye dayalı yeni bir tasarım yeniden yapılandırılabilir anten.
A novel design of wearable antenna depending on metamaterials inspired-fractal Minkowski-shaped for industrial, scientific, and medical (ISM) applications is presented. The antenna consists of a conventional monopole and a Chebyshev transformer coupled with a unit cell of a fractal Minkowski curve to obtain three bands covering the ISM and Wireless Local Area Network (WLAN) applications. To enhance the antenna performance, the authors proposed the Electromagnetic Band Gap (EBG) layer of 3×4 array is introduced into the design structure. The authors used material FR4 dielectric as a substrate to design the antenna with dimensions of 51mm x 45mm x 1.6mm and fed by a 50 Ω port. The Antenna performance is analyzed numerically using CST Microwave Studio (CSTMWS) depending on the Finite Integral Technique (FIT). Various investigation analyses have carried out to verify optimum antenna performance. The proposed antenna realizes reconfiguration by using the PIN diode. In both cases (switching= ON, OFF) the antenna achieves good bandwidth, |S11|<-10dB, and excellent impedance matching.
Resolving energy consumption issues and spectrum allocation for future broadband networks
The aim of this thesis is to resolve the energy consumption issues and determine the usage of energy or power with high spectrum allocation in future broadband networks with the help of clustering in data mining. The research work starts presenting an overview of the broadband network energy sector and the challenges it is facing; it is observed a change on the energy policies promoting the energy efficiency, encouraging an active role of the consumer, instructing them about the importance of the consumer behavior and also protecting consumer rights. Electricity is gaining room as energy source, its share will keep increasing constantly in the following decades. In this close future, broadband networks and smart meters' deployment will benefit both the utility and the consumer. In this environment, new services and new business appear, focusing on the energy management field and tools, they require specialization in fields such as, computer science, software development and data science. This research work has segmented the broadband networks according to the similarities of their electrical load profiles, using the proportion of energy usage per hour (%) as a common framework. The objective behind this energy consumption segmentation is to be able to provide personalized recommendations to each group in order to reduce their energy consumption and the associated costs, fostering energy efficiency measures and improving the consumer engagement. The desired segmentation is obtained by an iterative process, based on computational clusters calculation (using python programming language) and finalized by a post-clustering analysis applying visualization and statistical data mining technique to detect the energy consumption and reallocate them to a more appropriate group. The K-Means clustering technique was tested and compared, giving best prediction of accuracy 98.46% for all energy load profiles with high spectrum of 100GHz. The solution from the K-Means clustering is the one that better adapts to the segmentation sought, which is used as the base of the post-clustering stage to obtain the final energy consumption segmentation. Most of these methodologies use the absolute values in 100 kWh, as they were more focused on identify the users with higher energy savings potential. The energy consumption segmentation of the electricity consumers provides knowledge and a better understanding of the consumer. In this particular case, it allows to personalize energy savings recommendations according to the broadband networks specific characteristics; improving the consumer experience by being able to provide the adequate advices at the appropriate time, facts that increase the effectiveness of the energy efficiency advices' service for future broadband networks