SavedAdd your journal

Journals / İstanbul Ticaret Üniversitesi Teknoloji ve Uygulamalı Bilimler Dergisi / 2026 / Cilt: 9 Sayı: 1

TRADITIONAL AND DEEP LEARNING-BASED APPROACHES FOR FAKE MULTIMEDIA CONTENT GENERATION AND DETECTION

SAHTE MULTİMEDYA İÇERİK ÜRETİMİ VE TESPİTİNDE GELENEKSEL VE DERİN ÖĞRENME TABANLI YAKLAŞIMLAR

Marat Utepkaliyev(Milli Savunma Üniversitesi, Atatürk Stratejik Araştırmalar ve Lisansüstü Eğitim Enstitüsü, Bilgisayar Mühendisliği Anabilim Dalı)0009-0005-0605-6405
Aytuğ Boyacı(MİLLİ SAVUNMA ÜNİVERSİTESİ, HAVA HARP OKULU, BİLGİSAYAR MÜHENDİSLİĞİ BÖLÜMÜ)0000-0003-1016-3439
Pages
139–161
Publication Date
2026-08-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The presented study provides a comprehensive summary of existing approaches, identifies their limitations, and outlines future research directions for the development of automated fake multimedia detection technologies.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The emergence and advancement of deep learning technologies, particularly Generative Adversarial Networks (GANs), have enabled the generation of highly realistic synthetic multimedia content, commonly referred to as deepfakes.
📊
Key Findings & Data:Such artificially generated media pose a significant threat to the integrity of digital content, undermine public trust, and may be exploited for misinformation dissemination and cybercriminal activities.
💡
Conclusion & Impact:The presented study provides a comprehensive summary of existing approaches, identifies their limitations, and outlines future research directions for the development of automated fake multimedia detection technologies.
🔬Design:Review & Systematic Survey
📍Scope:Comprehensive Sample
⚙️Variables:Derin Öğrenme · Derin Sahte · Yapay Zeka

Abstract

The emergence and advancement of deep learning technologies, particularly Generative Adversarial Networks (GANs), have enabled the generation of highly realistic synthetic multimedia content, commonly referred to as deepfakes. Such artificially generated media pose a significant threat to the integrity of digital content, undermine public trust, and may be exploited for misinformation dissemination and cybercriminal activities. This paper presents a systematic review of existing literature on fake multimedia content generation methods and the approaches proposed for their detection. The review encompasses both traditional hand-crafted methods based on noise, texture, and geometric feature analysis, as well as modern deep learning-based approaches, including Convolutional Neural Networks (CNNs) and transformers. Particular emphasis is placed on the detection of artifacts specific to synthetic content, such as anomalies in the distribution of model output data, inconsistencies in pixel relationships, artifacts in the frequency domain, and traces of manipulation. The presented study provides a comprehensive summary of existing approaches, identifies their limitations, and outlines future research directions for the development of automated fake multimedia detection technologies.

Özet

Derin öğrenme teknolojilerinin, özellikle Çekişmeli Üretici Ağların (Generative Adversarial Networks, GAN) ortaya çıkışı ve gelişimi, Derin Sahte (Deepfake) olarak bilinen yüksek gerçekçi sentetik multimedyanın ortaya çıkmasına yol açmıştır. Bu doğal olmayan, yapay oluşturulan medya dosyaları, dijital içeriğin bütünlüğü için önemli bir tehdit oluşturmakta, toplumsal güveni zedelemekte ve yanlış bilgi yayımı ile siber suçlarda kullanılabilmektedir. Bu çalışmada, sahte multimedya üretim yöntemleri ve bunların tespitine yönelik yaklaşımlar üzerine mevcut literatür sistematik olarak incelenmektedir. İnceleme, gürültü, doku ve geometrik özellik analizine dayanan geleneksel el yapımı (hand-crafted) yöntemlerin yanı sıra, derin öğrenmeye dayalı modern yaklaşımları da kapsamaktadır. Bunların arasında Evrişimsel Sinir Ağları (Convolutional Neural Networks, CNN) ve transformerler yer almaktadır. Özellikle model çıkış verilerinin dağılımındaki anomaliler, piksel ilişkilerindeki tutarsızlıklar, frekans alanındaki artefaktlar ve manipülasyon izleri gibi sentetik içeriklere özgü artefaktların tespiti üzerinde durulmaktadır. Sunulan çalışma, mevcut yaklaşımların özetlenmesini, sınırlılıklarının belirlenmesini ve sahte multimedyanın otomatik tespiti teknolojilerinin geliştirilmesi için gelecekteki yönlerin tespit edilmesini sağlamaktadır.

🔖

Cite This Article

Utepkaliyev, M., Boyacı, A. (2026). TRADITIONAL AND DEEP LEARNING-BASED APPROACHES FOR FAKE MULTIMEDIA CONTENT GENERATION AND DETECTION. İstanbul Ticaret Üniversitesi Teknoloji ve Uygulamalı Bilimler Dergisi, Cilt: 9 Sayı: 1, 139–161. https://doi.org/10.56809/icujtas.1851374

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (50)

  1. Aggarwal, G., Srivastava, A.K., Jhajharia, K., Sharma, N.V. & Singh, G. (2023). Detection of deep fake images using convolutional neural networks. In 2023 3rd International Conference on Technological Advancements in Computational Sciences (ICTACS) (pp. 1083-1087). Tashkent, Uzbekistan.
  2. Al-Slais, Y. (2020). Privacy engineering methodologies: A survey. In 2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies (3ICT) (pp. 1-6). IEEE.
  3. Alhabeeb, S.K. & Al-Shargabi, A.A. (2024). Text-to-image synthesis with generative models: methods, datasets, performance metrics, challenges, and future direction. IEEE Access, 12, 24412-24427.
  4. Ardakani, S.P. & Kwong, C.F. (2023). Are fake images bothering you on social network? Let us detect them using recurrent neural network. IEEE Transactions on Computational Social Systems, 10(2), 783-794.
  5. Arif, D., Mehmood, Z., Ullah, A. & Winberg, S. (2023). High-definition image formation using multi-stage cycle generative adversarial network with applications in image forensic. Arabian Journal for Science and Engineering, 49, 3887-3896.
  6. Bhosale, A., Kaware, S., Varkale, R., Wagh, A. & Lavate, D. (2024). Image generation using GAN. International Research Journal of Innovations in Engineering and Technology (IRJIET), 8(3), 212-218.
  7. Bushey, J. (2023). AI-generated images as an emergent record format. In 2023 IEEE International Conference on Big Data (BigData), Sorrento, Italy, pp. 2020-2031.
  8. Chang, Y.-H., Chung, P.-H., Chai, Y.-H. & Lin, H.-W. (2024). Color face image generation with improved generative adversarial networks. Electronics, 13, 1205, 1-19.
  9. Chen, C., Liu, D., Ma, S., Nepal, S. & Xu, C. (2023). Private image generation with dual-purpose auxiliary classifier. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, pp. 20361-20370.
  10. Chen, J., Lo, M., Liao, H. & Huang, T. (2024). IPD-Net: detecting AI-generated images via inter-patch dependencies. International Journal of Advanced Computer Science and Applications, 15(7), 1372-1379.
  11. Cho, S.-H., Koh, S.-J. & Jung, K.-H. (2022). Image forensics using non-reducing convolutional neural network for consecutive dual operators. Applied Sciences, 12, 7152, 1-18.
  12. Chaitra, B. & Reddy, P.V.B. (2023). Digital image forgery: taxonomy, techniques, and tools – a comprehensive study. Int J Syst Assur Eng Manag, 14, 18-33.
  13. Concas, S., Perelli, G., Marcialis, G.L. & Puglisi, G. (2022). Tensor-based deepfake detection in scaled and compressed images. In 2022 IEEE International Conference on Image Processing (ICIP), Bordeaux, France, pp. 3121-3125.
  14. Convertini, V.N., Impedovo, D., Lopez, U., Pirlo, G. & Sterlicchio, G. (2024). Discrete Fourier transform in unmasking deepfake images: a comparative study of StyleGAN creations. Information, 15(11), 711, 1-23.
  15. Dang, M. & Nguyen, T.N. (2023). Digital face manipulation creation and detection: a systematic review. Electronics, 12(6), 3407, 1-37.
  16. Du, W. (2024). Design of artistic image generation and interactive painting system based on deep learning. J. Electrical Systems, 20(7s), 3089-3104.
  17. Dzhurov, A., Cherckesova, L. & Revyakina, E. (2022). Recognition of fake (spurious) video content synthesized using deepfake technology of the generative adversarial network (GAN) algorithm. Informatics, Computer Science and Management/Natural and Technical Sciences, 8, 68-80.
  18. Eremuk, V. & Romashov, V. (2023). Existing research, methods for creating fake images and ways to detect them. In Informatics, Computer Science and Management/ Natural and Technical Sciences, 7, 62-65.
  19. Elasri, M., Elharrouss, O., Al-Maadeed, S. & Tairi, H. (2022). Image generation: a review. Neural Processing Letters, 54, 4609-4646.
  20. Ghannad, N. & Passi, K. (2023). Detecting image forgery over social media using U-NET with Grasshopper Optimization. Algorithms, 16, 399, 1-24.
  21. Hao, Y., Chi, Z., Dong, L. & Wei, F. (2023). Optimizing prompts for text-to-image generation. In 37th Conference on Neural Information Processing Systems (NeurIPS 2023), Vancouver, Canada, pp. 1-17.
  22. Joshi, P. & V, N. (2024). Deep fake image detection using Xception architecture. In 2024 5th International Conference on Recent Trends in Computer Science and Technology (ICRTCST), Jamshedpur, India, pp. 533–537.
  23. Kar, P., Xue, Z., Ardakani, S.P. & Kwong, C.F. (2023). Are fake images bothering you on social network? Let us detect them using recurrent neural network. IEEE Transactions on Computational Social Systems, 10(2), 783- 794.
  24. Kaur, M., Daryani, P., Varshney, M. & Kaushal, R. (2022). Detection of fake images on WhatsApp using socio-temporal features. Social Network Analysis and Mining, 12(58), 1-13.
  25. Khudeyer, R.S. & Al-Moosawi, N.M. (2023). Fake image detection using deep learning. Informatica, 47, 115-120.
  26. Kiruthika, S. & Masilamani, V. (2023). Image quality assessment based fake face detection. Multimedia Tools and Applications, 82, 8691-8708.
  27. Kumari, R. & Garg, H. (2024). Image splicing forgery detection: a review. Multimedia Tools and Applications, 84, 1-39.
  28. Kumar, L. & Singh, D.K. (2024). Pose image generation for video content creation using controlled human pose image generation GAN. Multimedia Tools and Applications, 83, 59335-59354.
  29. Lai, J., Huo, Y., Hou, R. & Wang, X. (2022). A universal detection method for adversarial examples and fake images. Sensors, 22, 3445, 1-12.
  30. Li, J., Li, T., Lin, R. & Nie, Q. (2022). GAN-based models and applications. In 2022 IEEE 5th International Conference on Information Systems and Computer Aided Education (ICISCAE), Dalian, China, pp. 848-852.
  31. Li, J., Zhang, C., Zhu, W. & Ren, Y. (2024). A comprehensive survey of image generation models based on deep learning. Annals of Data Science, 12, 1-30.
  32. Luo, A., Kong, C., Huang, J., Hu, Y., Kang, X. & Kot, A.C. (2024). Beyond the prior forgery knowledge: mining critical clues for general face forgery detection. IEEE Transactions on Information Forensics and Security, 19, 1168-1182.
  33. Mishra, M., Jain, N.K. & Kumar, A. (2023). Reviewing image data: detecting forgery using a robust forensic method. SN Computer Science, 4(856), 1-11.
  34. Mukta, M.S.H., Ahmad, J., Raiaan, M.A.K., Islam, S., Azam, S., Ali, M.E. & Jonkman, M. (2023). An investigation of the effectiveness of deepfake models and tools. Journal of Sensor and Actuator Networks, 12, 61, 1-43.
  35. Park, J., Jeong, D., Lee, H., Han, S. & Paik, J. (2024). Prompt-based learning for image variation using single image multi-scale diffusion models. IEEE Access, 12, 158810-158823.
  36. Patel, Y., Tanwar, S., Bhattacharya, P., Gupta, R., Alsuwian, T., Davidson, I.E. & Mazibuko, T.F. (2023). An improved dense CNN architecture for deepfake image detection. IEEE Access, 11, 22081-22095.
  37. Polezhaeva, M.V., Kenzhina, D.S., Nerpin, E.S., Safonova, T.V. & Mokryak, A.V. (2024). Using a neural network to generate images. International Journal of Information Technology and Energy Efficiency, 9/8(46), 97-104.
  38. Porkodi, S.P., Sarada, V., Maik, V. & Gurushankar, K. (2023). Generic image application using GANs (Generative Adversarial Networks): a review. Evolving Systems, 14, 903-917.
  39. Raza, S.A., Habib, U., Usman, M., Cheema, A.A. & Khan, M.S. (2024). MMGANGuard: a robust approach for detecting fake images generated by GANs using multi-model techniques. IEEE Access, 12, 104153-104164.
  40. Rusin, M.I. & Weinstein, V.I. (2022). Methods for searching for synthetic changes in video recording. Information Security/Collection of Reports of the Russian School of Young Scientists, Novosibirsk, Russia, 24-28.
  41. Shahzad, H.F., Rustam, F., Flores, E.S., Mazón, J.L.V., de la Torre Diez, I. & Ashraf, I. (2022). A review of image processing techniques for deepfakes. Sensors, 22, 4556, 1-28.
  42. Sharma, H. & Das, S. (2023). A brief study of generative adversarial networks and their applications in image synthesis. Multimedia Tools and Applications, 83, 21551-21581.
  43. Shilaskar, S., Talewar, M., Tak, S. & Goud, S. (2024). GAN generated fake human face image detection. In 2024 International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), Bangalore, India, pp. 1-6.
  44. Vajpayee, H., Yadav, N., Raj, A. & Jhingran, S. (2023). Detecting deepfake human face images using transfer learning: a comparative study. In 2023 IEEE International Conference on Contemporary Computing and Communications (InC4), Bangalore, India, pp. 1-5.
  45. Verdoliva, L. (2020). Media forensics and deepfakes: an overview. IEEE Journal of Selected Topics in Signal Processing, 14(5), 910-932.
  46. Wang, S., Zhang, H., Yang, G., Guo, Z. & Chen, J. (2024). A two-stage fake face image detection algorithm with expanded attention. Multimedia Tools and Applications, 83, 55709-55730.
  47. Yadav, A. & Vishwakarma, D.K. (2024). Datasets, clues and state-of-the-arts for multimedia forensics: an extensive review. Expert Systems with Applications, 249, 1-36.
  48. Yoo, Y., Na, D., Nathanson, S., Cao, Y. & Watkins, L. (2024). Disinformation at scale: detecting AI-human composite images via convolution ensembles. In MILCOM 2024 - 2024 IEEE Military Communications Conference (MILCOM), Washington, DC, USA, pp. 621-626.
  49. Zhalgasbayev, A., Aiteni, T. & Khaimuldin, N. (2024). Using the CNN architecture based on the EfficientNetB4 model to efficiently detect deepfake images. In 2024 IEEE AITU: Digital Generation, Astana, Kazakhstan, pp. 14-19.
  50. Zou, Y., Luo, C. & Zhang, J. (2024). DIFLD: domain invariant feature learning to detect low-quality compressed face forgery images. Complex & Intelligent Systems, 10, 357-368.