Hakan Can Altunay

Dr. Hakan Can Altunay


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 December 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
HAHakan Can Altunay
Hakan Can Altunay
ZAZafer Albayrak
Zafer Albayrak
Short Message Service (SMS) still continues its existence despite the emergence of different messaging services. It plays a part in our lives as a communication service. Companies use SMS for advertisement purposes due to the fact that e-mail filtering systems have rooted, short message systems are being undersold by the operators, and spam detection and blocking systems used for short messages are ineffective. Individuals falling victim to SMS spam messages sent by malevolent persons incur pecuniary and non-pecuniary losses. The aim of this study is to present a hybrid model proposal with the intention of detecting SMS spam messages. This detection model uses a gated recurrent unit (GRU) and convolutional neural network (CNN) as two deep learning methods. However, the fact that both algorithms require high memory capacities is a limitation. The design for this model was laid out by using two different datasets containing combined text messages written in the Turkish and English languages. The datasets used in the study are TurkishSMSCollection and the SMS Spam dataset from the UCI database. The testing process was performed on the dataset through benchmarking as well as other machine learning algorithms. It was revealed in the study that the hybrid CNN + GRU approach attained an accuracy of 99.07% by demonstrating a better performance compared to the other algorithms.

26 October 2024
Verified
Conference Paper
Closed access
HAHakan Can Altunay
Hakan Can Altunay
SQL injection attack is one of the cyber attack types that puts individuals and institutions in a difficult situation in terms of data disclosure and material damage. This attack type, which is frequently preferred due to its case of use, has emerged with different usage features in recent years. In this study, various machine learning algorithms were tested to detect SQL Injection attacks. In the data pre-processing section, feature extraction was performed using Natural Language Processing techniques. While the relevance of expressions to each other was calculated with the Word Level TF-IDF method, term search was also performed. In the study, the classification process was performed using convolutional neural network, support vector machine, naive bayes and logistic regression from machine learning methods. At the end of the experimental study, it was found that convolutional neural network was the model that detected SQL Injection attacks with the highest success.

15 September 2024 in Black Sea Journal of Engineering and Science
Verified
Journal Article
Open access
PDF file
HAHakan Can Altunay
Hakan Can Altunay
In the cybersecurity world, the concept of a honeypot is generally referred to as trap systems that have real system behaviors, intentionally leave a security gap, and aim to collect information about cybercriminals who want to access them. It is a computer system that sets itself as a target to attract cyberattacks like bait. It is used to imitate a target such as cyberattackers and to learn about attack attempts, ways of working, or to distract them from other targets. In this study, a VoIP-based honeypot was used to determine the profiles of cyberattacks and attackers. A network environment was created using a low-interaction honeypot to analyze the behavior of cyberattackers and identify the services frequently preferred by these individuals. The honeypot in the network environment was monitored for a period of 90 days. 105,308 events were collected regarding protocols such as Telnet, SIP, SSH, SMB, and HTTP. There was no complex malware attack on the observed system. The service that was most attacked was determined to be Telnet. It was determined that many attacks occurred from the same IP address, indicating that automatic scanning tools were used. According to the results obtained, the proposed method performed a detailed analysis of the services from which cyberattacks came and the behaviors of the people who carried out these attacks. In addition, the highest level of understanding of user interaction was achieved thanks to the VoIP-based honeypot.

28 July 2026 in Research Square
Verified
Preprint
Open access
PDF file
SCSoner Cankaya
Soner Cankaya
FAFatih Samet Atasoy
Fatih Samet Atasoy
MKMuhammet Kusan
Muhammet Kusan
MBMustafa Tolga Bayraktar
Mustafa Tolga Bayraktar
HAHakan Can Altunay
Hakan Can Altunay
EŞErkan Faruk Şirin
Erkan Faruk Şirin
Existing cybersecurity instruments largely focus on awareness, compliance, or behavioral intentions, while employees’ organizational cybersecurity perceptions remain insufficiently examined from a PMT-based appraisal perspective. This study aimed to develop and psychometrically validate the Organizational Cybersecurity Perception Scale, a Protection Motivation Theory (PMT)-based instrument contextualized by the NIST Cybersecurity Framework (CSF) 2.0. The scale was designed to assess employees’ cognitive appraisals of organizational cybersecurity threats, protective capacities, self-efficacy, and perceived response costs among individuals actively using institutional digital systems. NIST CSF 2.0 was used as a contextual framework during item development rather than as a latent measurement structure. Psychometric analyses were conducted using two independent samples drawn from different institutional sectors in Türkiye: an exploratory factor analysis sample (EFA; n = 519) and a confirmatory factor analysis sample (CFA; n = 400). EFA revealed a six-factor structure consisting of Perceived Severity, Perceived Vulnerability, Preventive Efficacy, Intervention Capability, Self-Efficacy, and Response Cost. This structure indicated that response efficacy differentiated into prevention-oriented and incident-management-oriented dimensions in the organizational cybersecurity context. The final scale included 27 items. Cronbach’s alpha coefficients ranged from .762 to .862, and the overall scale demonstrated good internal consistency (α = .863). CFA supported the modified six-factor measurement model with acceptable overall fit indices (χ²/df = 1.761, RMSEA = .044, RMR = .040, CFI = .952, IFI = .953). Composite reliability values ranged from .727 to .866, and average variance extracted values provided acceptable evidence for convergent validity. HTMT ratios supported discriminant validity, and common method bias assessments did not indicate a substantial threat to the measurement model. Additional known-groups analyses conducted in two context-specific samples (public sports institutions, n = 188; university employees, n = 113) showed that the scale differentiated theoretically relevant groups according to cybersecurity training, incident awareness, policy/procedure awareness, and cybersecurity unit awareness. Overall, the findings indicate that the PMT-OCPS provides researchers and organizations with a theory-driven instrument for assessing organizational cybersecurity perception and evaluating human-centered cybersecurity readiness

7 October 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
HAHakan Can Altunay
Hakan Can Altunay
ASAhmet Doğukan Sarıyalçınkaya
Ahmet Doğukan Sarıyalçınkaya
Artificial Intelligence technology has been frequently used in the personalized healthcare services domain in recent years. The quality of medical services has been improved and a new era has started for healthcare services with the use of Artificial Intelligence. Simultaneously, deep learning models, which are qualified as a special use of Artificial Intelligence, are preferred depending on the number of users and the amount of data increasing with each passing day. This study proposes a BERT-based medical chatbot architecture that combines contextual natural language processing with an application-level cryptographic protection layer for client-server communication. The cryptographic mechanism is intended as an additional protection layer around the transmitted chatbot payload and is not presented as a replacement for standard TLS or as a mechanism for protecting plaintext data during server-side inference. The NLP component uses a BERT-based Transformer model to process medical queries from the HealthFC and TREC-Health datasets. The experimental implementation was developed using the Hugging Face Transformers library with TensorFlow and spaCy, and the model was evaluated using accuracy, precision, recall, F1-score, and AUC-ROC. Five-fold stratified cross-validation was also employed to examine the consistency of the classification performance across data partitions. For communication security, RSA is used for the distribution of the AES secret key, AES is used to encrypt the transmitted medical payload, and SHA-256-based HMAC is employed to provide message integrity and authentication. The proposed model achieved 99% accuracy, 99% precision, 97% recall, 98% F1-score, and 97% AUC-ROC. In the five-fold evaluation, the accuracy values were 1.00, 0.99, 0.99, 0.98, and 0.99, respectively. Compared with the evaluated LSTM, SVM, and Bi-LSTM baselines, which achieved accuracies of 0.88, 0.91, and 0.94, respectively, the proposed BERT-based model achieved the highest classification performance. These results indicate strong classification performance on the evaluated benchmark datasets, while the cryptographic layer provides an additional application-level mechanism for protecting medical information during client-server communication. The proposed security mechanism should be interpreted within this scope: it complements, rather than replaces, TLS and does not protect plaintext medical data after decryption on the server during inference. The study establishes a BERT-based and security-oriented architecture for medical chatbot applications; however, clinical safety, external validation, paraphrase-aware leakage analysis, end-to-end latency, and multilingual or voice-based capabilities require further experimental evaluation.