Ebu Yusuf Güven
Research Subjects
Ebu Yusuf Güven has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Ahmet Alp Orakçi1 shared publication
- Ali Boyaci
Oak Ridge National Laboratory, Oak Ridge, TN, USA
1 shared publication Ali Yilmaz Camurcu
Fatih Sultan Mehmet Vakıf üniversitesi
1 shared publicationBehice Bakir
Istanbul University-Cerrahpasa Computer Engineering,Istanbul,Trkiye
1 shared publication- Fatma Nur Sarıtemur
Department of Computer Engineering, stanbul niversity-Cerrahpasa, Istanbul, Trkiye
1 shared publication Gizem Sütçü
Department of Computer Engineering, stanbul niversity-Cerrahpasa, Istanbul, Trkiye
1 shared publication
Latest Publications
- 16 June 2026
- Published by Springer Nature
- p. 201-211
Spectre Attacks Detection in RISC-V Processors Using Hardware-Level Machine Learning Models
- 16 June 2026
- Published by Springer Nature
- p. 201-211
Spectre Attacks Detection in RISC-V Processors Using Hardware-Level Machine Learning Models
- 9 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (3) , 7100-7110
Evaluation of Phishing Attacks Targeting Local Systems Using an Attribute-Based Dataset and Machine Learning Methods
Phishing attacks are a form of social engineering that deceives users by imitating legitimate websites to steal sensitive information. This study focuses on phishing attacks tar geting local systems and introduces a newly developed attribute based dataset for detecting such attacks. The proposed dataset consists of 31 attributes derived from URL- and similarity based features. To assess the impact of feature engineering, three distinct datasets were generated, and their performance was compared across multiple classifiers. Several machine learning algorithms, including Decision Tree, Random Forest, Logistic Regression, Support Vector Machine, and Artificial Neural Network, are applied to evaluate classification performance. Experimental results demonstrate high accuracy in detecting phishing attacks on local systems, with the Logistic Regression method achieving the best result of 96.40%. Furthermore, validation on a publicly available dataset from Kaggle yielded an accuracy of 97.48%, confirming the model's strong generalization capability. These findings highlight the effectiveness of attribute-based datasets combined with machine learning approaches for improving phishing detection in real-world environments.
- 9 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (3) , 7100-7110
Evaluation of Phishing Attacks Targeting Local Systems Using an Attribute-Based Dataset and Machine Learning Methods
Phishing attacks are a form of social engineering that deceives users by imitating legitimate websites to steal sensitive information. This study focuses on phishing attacks tar geting local systems and introduces a newly developed attribute based dataset for detecting such attacks. The proposed dataset consists of 31 attributes derived from URL- and similarity based features. To assess the impact of feature engineering, three distinct datasets were generated, and their performance was compared across multiple classifiers. Several machine learning algorithms, including Decision Tree, Random Forest, Logistic Regression, Support Vector Machine, and Artificial Neural Network, are applied to evaluate classification performance. Experimental results demonstrate high accuracy in detecting phishing attacks on local systems, with the Logistic Regression method achieving the best result of 96.40%. Furthermore, validation on a publicly available dataset from Kaggle yielded an accuracy of 97.48%, confirming the model's strong generalization capability. These findings highlight the effectiveness of attribute-based datasets combined with machine learning approaches for improving phishing detection in real-world environments.
- Open Access
- 7 January 2025
- Published by Balkan Journal of Electrical & Computer Engineering (BAJECE) in Balkan Journal of Electrical and Computer Engineering
- Vol. 12 (4) , 337-348
Analysis of Malicious Files Gathering via Honeypot Trap System and Benchmark of Anti-Virus Software
In the age of widespread digital integration, the rise in cyber threats is evident. Cyber attackers use malicious software (malware) to compromise data and exploit system resources, employing tactics such as remote control or ransom through data encryption. Despite the common use of antivirus software with signature-based detection, this study reveals its limitations. Using a honeypot trap system on Google Cloud, suspicious files uploaded by attackers were analyzed. Results from evaluating these files with 64 antivirus programs show that relying solely on signature-based methods is insufficient. Only three programs had success rates exceeding 90\%, while the majority had success rates predominantly below 70\%. This underscores the need for diverse detection techniques alongside signature-based methods to enhance cybersecurity. The repository containing collected malicious files and the Python script is available on Github, serving as a valuable research resource for further exploration.
- 7 January 2025
- Published by Balkan Journal of Electrical & Computer Engineering (BAJECE) in Balkan Journal of Electrical and Computer Engineering
- Vol. 12 (4) , 337-348
Open AccessAnalysis of Malicious Files Gathering via Honeypot Trap System and Benchmark of Anti-Virus Software
In the age of widespread digital integration, the rise in cyber threats is evident. Cyber attackers use malicious software (malware) to compromise data and exploit system resources, employing tactics such as remote control or ransom through data encryption. Despite the common use of antivirus software with signature-based detection, this study reveals its limitations. Using a honeypot trap system on Google Cloud, suspicious files uploaded by attackers were analyzed. Results from evaluating these files with 64 antivirus programs show that relying solely on signature-based methods is insufficient. Only three programs had success rates exceeding 90\%, while the majority had success rates predominantly below 70\%. This underscores the need for diverse detection techniques alongside signature-based methods to enhance cybersecurity. The repository containing collected malicious files and the Python script is available on Github, serving as a valuable research resource for further exploration.
- 26 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
EKF Based Localization: Integrating IMU and LiDAR Data in the Hilti SLAM Challenge
With the development of robotics and artificial intelligence technology, autonomous driving vehicles have become an attractive topic in industry and academia. In order to navigate safely, it is necessary for the surrounding environment to form an accurate representation and for the robot to estimate accurately for positioning. Simultaneous Localization and Mapping (SLAM) method is considered as a good solution for localization and navigation of autonomous driving vehicles. One of the most important factors for SLAM is the ability of the robot to make optimal position estimates. In this study, a multi-sensor Hilti SLAM Challenge dataset, which was created in different and challenging scenarios for mobile robot position estimation, was studied on the data taken from a building under construction. Sensor fusion was performed to use IMU and LIDAR data together. Extended Kalman Filter (EKF), a common estimation algorithm, was used to estimate the position of the building. Location estimation results were compared with ground truth values and the method was improved according to the comparison results. A Mean Absolute Error (MAE) value of approximately 2.4 was obtained. It was noted that the position estimates were improved with sensor fusion, the developed algorithm and the simulations performed on the data set containing various difficulties.
- 26 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
EKF Based Localization: Integrating IMU and LiDAR Data in the Hilti SLAM Challenge
With the development of robotics and artificial intelligence technology, autonomous driving vehicles have become an attractive topic in industry and academia. In order to navigate safely, it is necessary for the surrounding environment to form an accurate representation and for the robot to estimate accurately for positioning. Simultaneous Localization and Mapping (SLAM) method is considered as a good solution for localization and navigation of autonomous driving vehicles. One of the most important factors for SLAM is the ability of the robot to make optimal position estimates. In this study, a multi-sensor Hilti SLAM Challenge dataset, which was created in different and challenging scenarios for mobile robot position estimation, was studied on the data taken from a building under construction. Sensor fusion was performed to use IMU and LIDAR data together. Extended Kalman Filter (EKF), a common estimation algorithm, was used to estimate the position of the building. Location estimation results were compared with ground truth values and the method was improved according to the comparison results. A Mean Absolute Error (MAE) value of approximately 2.4 was obtained. It was noted that the position estimates were improved with sensor fusion, the developed algorithm and the simulations performed on the data set containing various difficulties.
- Open Access
- 14 December 2023
- Published by Springer Nature in Research Square
Analysis of Malicious Files Gathering via Honeypot Trap System and Benchmark of Anti-Virus Software
In an era dominated by the pervasive integration of digital technologies, the surge in cyber threats is increasingly conspicuous. Cyber attackers employ malicious software (Malware) to compromise data integrity and exploit system resources. Tactics include transforming devices into remotely controlled assets or extorting ransom through data encryption. While end users commonly resort to antivirus software with signature-based detection, the protracted and dangered of malware detection necessitates alternative approaches. This study addresses this need by utilizing a honeypot trap system on Google Cloud to analyze suspicious files uploaded by attackers. Evaluated through a signature-based method, these files using 64 antivirus programs underscore the inadequacy of relying solely on this approach, with only three exhibiting success rates exceeding 90%. The majority, 61 antivirus programs, showed success rates predominantly below 70%. This underscores a crucial conclusion: sole reliance on signature-based security falls short in combating contemporary cyber threats. The study advocates for diverse detection techniques, independent or concurrent with signature-based methods, to fortify cybersecurity. The repository containing the honeypot-collected malicious files and Python script is publicly available on Github, serving as a valuable research resource.
- 14 December 2023
- Published by Springer Nature in Research Square
Open AccessAnalysis of Malicious Files Gathering via Honeypot Trap System and Benchmark of Anti-Virus Software
In an era dominated by the pervasive integration of digital technologies, the surge in cyber threats is increasingly conspicuous. Cyber attackers employ malicious software (Malware) to compromise data integrity and exploit system resources. Tactics include transforming devices into remotely controlled assets or extorting ransom through data encryption. While end users commonly resort to antivirus software with signature-based detection, the protracted and dangered of malware detection necessitates alternative approaches. This study addresses this need by utilizing a honeypot trap system on Google Cloud to analyze suspicious files uploaded by attackers. Evaluated through a signature-based method, these files using 64 antivirus programs underscore the inadequacy of relying solely on this approach, with only three exhibiting success rates exceeding 90%. The majority, 61 antivirus programs, showed success rates predominantly below 70%. This underscores a crucial conclusion: sole reliance on signature-based security falls short in combating contemporary cyber threats. The study advocates for diverse detection techniques, independent or concurrent with signature-based methods, to fortify cybersecurity. The repository containing the honeypot-collected malicious files and Python script is publicly available on Github, serving as a valuable research resource.
- 8 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 11 (2) , 2776-2783
ICON: Instagram Profile Classification Using Image and Natural Language Processing Methods
The use of social media has grown significantly, and businesses are now using these platforms to promote their products and services. To do this, companies have created business accounts on social networks. However, social media platforms can also be a breeding ground for unwanted behaviors such as cyberbullying, sexual content, and promotional comments. To address this issue, a study was conducted to create a system that could classify public accounts on Instagram by analyzing comments, profile pictures, bios, and posts shared by users with business accounts. First, a crawler was developed, and data were collected using this crawler and then anonymized. Next, the collected data were processed using natural language processing (NLP) techniques for text and image processing methods for images to extract features and create a dataset. Nearly 10 000 profiles and 30 000 comments from public accounts were manually tagged to create the classification model. The final model had an accuracy rate of 95% on the dataset, allowing for the effective identification of different types of business accounts on Instagram.
- 8 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 11 (2) , 2776-2783
ICON: Instagram Profile Classification Using Image and Natural Language Processing Methods
The use of social media has grown significantly, and businesses are now using these platforms to promote their products and services. To do this, companies have created business accounts on social networks. However, social media platforms can also be a breeding ground for unwanted behaviors such as cyberbullying, sexual content, and promotional comments. To address this issue, a study was conducted to create a system that could classify public accounts on Instagram by analyzing comments, profile pictures, bios, and posts shared by users with business accounts. First, a crawler was developed, and data were collected using this crawler and then anonymized. Next, the collected data were processed using natural language processing (NLP) techniques for text and image processing methods for images to extract features and create a dataset. Nearly 10 000 profiles and 30 000 comments from public accounts were manually tagged to create the classification model. The final model had an accuracy rate of 95% on the dataset, allowing for the effective identification of different types of business accounts on Instagram.
- 1 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 248-253
Edge Computing Security Application: Kılıç
Intelligent systems change familiar objects as well as rapidly change common technologies. Internet of Things (IoT) applications are made with Cloud Computing can not meet the expectation of service quality due to bandwidth and network delays. It focuses on solving these needs in real-time intelligent applications that use Edge Computing, which is introduced as a new platform between the cloud and the objects. Security and privacy concerns are a major obstacle to the widespread use of intelligent objects. Edge Computing has both its proximity to objects and sufficient resources are available to provide an environment for the operation of security applications. In this study, Edge Computing is introduced. Edge Computing Security Aplication Kılıç is recommend, which works on the Edge Layer. To illustrate the effective use of the Kılıç, the real-time industry application has been shown in the context of the Smart Factory.
- 1 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 248-253
Edge Computing Security Application: Kılıç
Intelligent systems change familiar objects as well as rapidly change common technologies. Internet of Things (IoT) applications are made with Cloud Computing can not meet the expectation of service quality due to bandwidth and network delays. It focuses on solving these needs in real-time intelligent applications that use Edge Computing, which is introduced as a new platform between the cloud and the objects. Security and privacy concerns are a major obstacle to the widespread use of intelligent objects. Edge Computing has both its proximity to objects and sufficient resources are available to provide an environment for the operation of security applications. In this study, Edge Computing is introduced. Edge Computing Security Aplication Kılıç is recommend, which works on the Edge Layer. To illustrate the effective use of the Kılıç, the real-time industry application has been shown in the context of the Smart Factory.