Publications 2
Preprints 3
Research Areas AI Security, Deepfake Detection, Secure Systems, Software Security
Reviewer JOSS, JORS
My research focuses on applied cybersecurity, artificial intelligence security, secure software engineering, secure systems design, and cybersecurity education. This page provides access to my peer-reviewed publications, preprints, and publicly available research artifacts.
Peer-Reviewed Publications
Audio-Visual Synchronization Analysis for Deepfake Detection: A Comprehensive Review
Halil Ibrahim Dursunoglu (2026)
International Journal of Computer Techniques (IJCT)
This review examines synchronization-based approaches for deepfake detection and discusses challenges related to AI-generated media, digital trust, and multimedia forensics.
DOI: 10.5281/zenodo.19557051
Human Activity Monitoring with Wearable Sensors and Hybrid Classifiers
G. Uslu, H. I. Dursunoglu, O. Altun, S. Baydere (2013)
International Journal of Computer Information Systems and Industrial Management
This work investigates activity recognition using wearable sensors and hybrid classification techniques for intelligent monitoring systems.
Preprints
Hybrid Classification for Complex and Composite Activity Recognition in Multi-User Environments
Halil Ibrahim Dursunoglu (2026)
This work proposes a hybrid framework for recognizing complex activities, interactions, and user attribution in multi-user environments using wearable sensor data.
DOI: 10.5281/zenodo.20549987
SEMA-GUARD: Semantic and Graph-Based Vulnerability Detection in Assembly Code
Halil Ibrahim Dursunoglu, K. Sulkalar (2026)
SEMA-GUARD introduces a semantic and graph-based approach for detecting security weaknesses in assembly language programs and low-level software systems.
DOI: 10.5281/zenodo.20550170
Security Weaknesses in LLM-Generated Source Code: An Empirical Vulnerability Analysis of Iterative AI-Assisted Development
Halil Ibrahim Dursunoglu, K. Sulkalar (2026)
This study investigates how security vulnerabilities evolve during iterative AI-assisted software development and proposes methods for evaluating security drift across development cycles.
DOI: 10.5281/zenodo.20550245
Research Artifacts
Research software, datasets, preprints, and supporting materials are publicly available through the following platforms:
GitHub
Source code, software prototypes, educational security labs, and research implementations.
Zenodo
Publications, preprints, datasets, and archived research artifacts with DOI assignment.
Google Scholar
Citation records, publication metrics, and indexing information.
ORCID
Persistent researcher identifier and publication record.