Person: ŞAHİNGÖZ, ÖZGÜR KORAY
Loading...
Email Address
Birth Date
Research Projects
Organizational Units
Job Title
Last Name
ŞAHİNGÖZ
First Name
ÖZGÜR KORAY
Name
7 results
Search Results
Now showing 1 - 7 of 7
Publication Open Access Derin Öğrenme Yöntemleri ile Borsada Fiyat Tahmini(Bitlis Eren Üniversitesi Rektörlüğü, 2020) Şişmanoğlu, Gözde; Koçer, Furkan; Önde, Mehmet ali; ŞAHİNGÖZ, ÖZGÜR KORAYSon yıllarda, bilgisayarların donanımındaki teknolojik gelişmeler ve makine öğrenme tekniklerindeki gelişmeler nedeniyle, "Büyük Veri" ve "Paralel İşleme" kullanımı olmak üzere problem çözmek için iki artan yaklaşım vardır. Özellikle GPU'lar gibi çok çekirdekli bilgi işlem aygıtlarında paralel olarak gerçekleştirilebilen Derin Öğrenme algoritmalarının ortaya çıkmasıyla, bu yaklaşımlarla birçok gerçek dünya problemleri çözülebilmektedir. Derin öğrenme modelleri eğitildikleri veri ile sınıflandırma, regresyon analizi ve zaman serilerinde tahmin gibi uygulamalarda büyük başarılar göstermektedir. Bu modellerin finansal piyasadaki en aktif uygulama alanlarından biri özellikle borsada işlem gören hisse senetlerinin tahmini işlemleridir. Bu alanda amaç, pazardaki değişim süreci hakkındaki hisse senedinin önceki günlük verilerine bakarak kısa veya uzun vadeli gelecekteki değerini tahmin etmeye çalışmaktır. Bu çalışmada, LSTM, GRU ve BLSTM isimli 3 farklı derin öğrenme modeli kullanılarak bir hisse senedi tahmin sistemi geliştirilip, kullanılan modeller arasında karşılaştırmalı bir analiz yapıldı. Spekülatif hareketlerden uzak olması için veri seti olarak 1968'den 2018'e kadar olan New York Borsası'ndan hisse senedinin zaman serisi değerlerini kullanıldı. Spesifik olarakta IBM hisse senedi ile test çalışmaları yapıldı. Deneysel sonuçlar BLSTM modelinin 5 günlük girdi verileriyle eğitilmesi ile %63,54 lük bir yönsel doğruluk değerine ulaşıldığını göstermektedir.Publication Restricted Detection of Phishing Websites by Using Machine Learning-Based URL Analysis(Institute of Electrical and Electronics Engineers Inc., 2020) Korkmaz, Mehmet; ŞAHİNGÖZ, ÖZGÜR KORAY; Diri, BanuIn recent years, with the increasing use of mobile devices, there is a growing trend to move almost all real-world operations to the cyberworld. Although this makes easy our daily lives, it also brings many security breaches due to the anonymous structure of the Internet. Used antivirus programs and firewall systems can prevent most of the attacks. However, experienced attackers target on the weakness of the computer users by trying to phish them with bogus webpages. These pages imitate some popular banking, social media, e-commerce, etc. sites to steal some sensitive information such as, user-ids, passwords, bank account, credit card numbers, etc. Phishing detection is a challenging problem, and many different solutions are proposed in the market as a blacklist, rule-based detection, anomaly-based detection, etc. In the literature, it is seen that current works tend on the use of machine learning-based anomaly detection due to its dynamic structure, especially for catching the 'zero-day' attacks. In this paper, we proposed a machine learning-based phishing detection system by using eight different algorithms to analyze the URLs, and three different datasets to compare the results with other works. The experimental results depict that the proposed models have an outstanding performance with a success rate.Publication Open Access Increasing the Performance of Machine Learning-Based IDSs on an Imbalanced and Up-to-Date Dataset(IEEE, 2020) BAYDOĞMUŞ, GÖZDE KARATAŞ; Demir, Önder; ŞAHİNGÖZ, ÖZGÜR KORAYIn recent years, due to the extensive use of the Internet, the number of networked computers has been increasing in our daily lives. Weaknesses of the servers enable hackers to intrude on computers by using not only known but also new attack-types, which are more sophisticated and harder to detect. To protect the computers from them, Intrusion Detection System (IDS), which is trained with some machine learning techniques by using a pre-collected dataset, is one of the most preferred protection mechanisms. The used datasets were collected during a limited period in some specific networks and generally don & x2019;t contain up-to-date data. Additionally, they are imbalanced and cannot hold sufficient data for all types of attacks. These imbalanced and outdated datasets decrease the efficiency of current IDSs, especially for rarely encountered attack types. In this paper, we propose six machine-learning-based IDSs by using K Nearest Neighbor, Random Forest, Gradient Boosting, Adaboost, Decision Tree, and Linear Discriminant Analysis algorithms. To implement a more realistic IDS, an up-to-date security dataset, CSE-CIC-IDS2018, is used instead of older and mostly worked datasets. The selected dataset is also imbalanced. Therefore, to increase the efficiency of the system depending on attack types and to decrease missed intrusions and false alarms, the imbalance ratio is reduced by using a synthetic data generation model called Synthetic Minority Oversampling TEchnique (SMOTE). Data generation is performed for minor classes, and their numbers are increased to the average data size via this technique. Experimental results demonstrated that the proposed approach considerably increases the detection rate for rarely encountered intrusions.Publication Metadata only Machine Learning Based Phishing Detection from URIs(2017-12) Buber, Ebubekir; Demir, Önder; Diri, Banu; ŞAHİNGÖZ, ÖZGÜR KORAY; 214903Due to the rapid growth of the Internet, users change their preference from traditional shopping to the electronic commerce. Instead of bank/shop robbery, nowadays, criminals try to find their victims in the cyberspace with some specific tricks. By using the anonymous structure of the Internet, attackers set out new techniques, such as phishing, to deceive victims with the use of false websites to collect their sensitive information such as account IDs, usernames, passwords, etc. Understanding whether a web page is legitimate or phishing is a very challenging problem, due to its semantics-based attack struc ture, which mainly exploits the computer users’ vulnerabilities. Although software companies launch new anti-phishing products, which use blacklists, heuristics, visual and machine learning-based approaches, these products cannot prevent all of the phishing attacks. In this paper, a real-time anti-phishing system, which uses seven different classification algorithms and natural language processing (NLP) based features, is proposed. The system has the following distinguishing properties from other studies in the literature: language independence, use of a huge size of phishing and legitimate data, real-time execution, detection of new websites, independence from third-party services and use of feature-rich classifiers. For mea suring the performance of the system, a new dataset is constructed, and the experimental results are tested on it. According to the experimental and comparative results from the implemented classification algorithms, Random Forest algorithm with only NLP based features gives the best performance with the 97.98% accuracy rate for detection of phishing URLs.Publication Restricted Malware Detection in Android Systems with Traditional Machine Learning Models: A Survey(IEEE, 2020) Bayazit, Esra Çalık; ŞAHİNGÖZ, ÖZGÜR KORAY; Doğan, BuketDue to the increased number of mobile devices, they are integrated in every dimension of our daily life. To execute some sophisticated programs, a capable operating must be set up on them. Undoubtedly, Android is the most popular mobile operating system in the world. IT is extensively used both in smartphones and tablets with an open source manner which is distributed with Apache License. Therefore, many mobile application developers focused on these devices and implement their products. In recent years, the popularity of Android devices makes it a desirable target for malicious attackers. Especially sophisticated attackers focused on the implementation of Android malware which can acquire and/or utilize some personal and sensitive data without user consent. It is therefore essential to devise effective techniques to analyze and detect these threats. In this work, we aimed to analyze the algorithms which are used in malware detection and making a comparative analysis of the literature. With this study, it is intended to produce a comprehensive survey resource for the researchers, which aim to work on malware detection.Publication Metadata only Autonomous vehicle control for Lane and vehicle tracking by using deep learning via vision(2018) Olgun, Masum Celil; Baytar, Zakir; Akpolat, Kadir Metin; ŞAHİNGÖZ, ÖZGÜR KORAYCamera-based lane detection and vehicle tracking algorithms are one of the keystones for many autonomous systems. The navigational process of those systems is mainly focused on the output of detection algorithms. However, detection algorithms for lane detection need more pre-processing time and computational effort. They are also affected by environmental conditions and must regularly be improved. In this paper machine learning techniques and computer vision algorithms are utilized for the tasks of the lane and vehicle tracking of an autonomous vehicle control scenario. With the nature of used learning algorithm, the proposed system can handle complex image problems. The vehicle, on which we implement our algorithms, can manage to carry out the following tasks autonomously; tracking the lanes, following another vehicle, and stopping in necessary conditions. For that, one of the primary purposes is image-based lane tracking methodology by using learning algorithms. Data augmentation is applied to create diversity for the dataset. Application in this methodology has been discussed. For lane tracking Convolutional Neural Network architecture which is based on NVIDIA's PilotNet is preferred. For detecting objects and vehicles, the system is trained on the faster region-based convolutional neural network (Faster R-CNN) to identify traffic light and stop sign are by Haar Cascade Classifier. All these learning models are trained on NVIDIA GTX 1070 Graphics Processing Unit (GPU) to reduce training time. Experimental results showed that the proposed system gives a favorable result to autonomously control vehicles for lane and vehicle tracking purposes by vision.Publication Restricted Feature Selections for the Classification of Webpages to Detect Phishing Attacks: A Survey(IEEE, 2020) Korkmaz, Mehmet; ŞAHİNGÖZ, ÖZGÜR KORAY; Diri, BanuIn recent years, due to the increased number of Internet-connected devices, almost all the real-world interactions are transferred to the cyberworld. Therefore, most of the commerce (especially in the e-commerce format) are executed over webpages. The anonymous and uncontrollable structure of Internet, enables the malicious use of this cyber environment for a relatively new crime format, named as e-crime, which mainly aims some illegal financial gain by cheating the standard end-users. Phishing attacks are one of the most preferred fraudulent technique which is used for getting some confidential information (like user-id, password, credit card information, etc.) of the end-users. Therefore, security admins of the networks try to decrease the number of victims is their companies. One principal protection mechanism is the use of blacklists to detect the phishing webpages. However, it has a significant deficiency in not protection about new page attacks. Most of the security admins use some learning systems which are trained by a pre-collected a-dataset by extracting some features from the URL and content of the web pages. The performance of the used system directly related with the features used for the classification. In this work, we aimed to analyze the previously used features in the classification of the web pages by making a comparative analysis about the literature. With this study, it is aimed to produce a general survey resource for the researchers, which aim to work on the classification of webpages or the security of the networks.