CNN-Based Image Forgery Detection Using ELA (Error Level Analysis)

Yıl 2025, Cilt: 7 Sayı: 1, 41 - 50, 30.04.2025

Elnur Osmanov , İclal Çetin Taş

https://doi.org/10.46387/bjesr.1580950

Öz

In today's world, image forgery has become a significant issue threatening information security in digital environments. With the rapid spread of digital media, instances of image manipulation have increased, making reliable information sharing more difficult. In this context, image forgery emerges as one of the most critical information security issues of the digital age.

This study aims to detect image forgery using Error Level Analysis (ELA) and Convolutional Neural Networks (CNN). Initially, the fundamental principles and application methods of ELA are discussed, followed by a detailed examination of the architecture and training processes of CNN. Experiments conducted on the Casia, Columbia, and hybrid datasets have shown that the proposed method achieves high accuracy rates. The findings indicate that the combination of ELA and CNN serves as an effective tool for detecting image forgery. The F1 Score obtained at the end of the experiments was calculated to be 0.94, emphasizing the method's effectiveness.

Anahtar Kelimeler

Deep Learning , Image Forgery Detection , ELA. , CNN

ELA (Error Level Analysis) kullanarak CNN Tabanlı Görüntü Sahteciliği Tespiti

Öz

Günümüzde görüntü sahteciliği, dijital ortamda bilgi güvenliğini tehdit eden önemli bir sorun haline gelmiştir. Dijital medyanın hızla yayılmasıyla birlikte, görüntü manipülasyonları artış göstermiş ve güvenilir bilgi paylaşımını zorlaştırmıştır. Bu bağlamda, görüntü sahteciliği, dijital çağın en önemli bilgi güvenliği sorunlarından biri olarak öne çıkmaktadır.

Bu çalışmada, Hata Seviyesi Analizi (ELA) ve Derin Sinir Ağları (CNN) kullanılarak görüntü sahteciliğinin tespit edilmesi amaçlanmıştır. İlk olarak ELA'nın temel prensipleri ve uygulama yöntemleri ele alınmış, ardından CNN'in mimarisi ve eğitim süreçleri detaylandırılmıştır. Casia, Columbia ve hibrit veri setleri üzerinde gerçekleştirilen deneyler sonucunda, önerilen yöntemin yüksek doğruluk oranlarına ulaştığı gözlemlenmiştir. Elde edilen bulgular, ELA ve CNN kombinasyonunun görüntü sahteciliği tespitinde etkili bir araç olduğunu ortaya koymaktadır. Deneyler sonunda CNN vee la beraber kullanıldığından en yüksek F1-skor değeri 0.94 bulunmuştur.

Anahtar Kelimeler

Derin Öğrenme , Görüntü Sahteciliği Tespiti , ELA , CNN

Kaynakça

• K. Vijayalakshmi, J. Sasikala ve C. Shanmuganathan, “Copy-paste forgery detection using deep learning with error level analysis”, Multimedia Tools and Applications, vol. 83, pp. 3425–3449, 2024.
• M.M. Isaac ve M. Wilscy, “Image forgery detection based on Gabor wavelets and local phase quantization”, Procedia Computer Science, vol. 58, pp. 76–83, 2015.
• A. Doegar, S. Hiriyannaiah, S.G. Matt, S.K. GopalIyengar ve M. Dutta, “Image forgery detection based on fusion of lightweight deep learning models”, Turkish Journal of Electrical Engineering and Computer Sciences, cilt 29, sayı 4, ss. 1978–1993, 2021.
• H. Farid, “Image forgery detection”, IEEE Signal Processing Magazine, vol. 26, no. 2, pp. 16–25, 2009.
• D.Y. Liliana and T. Basaruddin, “Deteksi pemalsuan citra berbasis dekomposisi nilai singulir,” MAKARA Sci. Ser., vol. 13, no. 2, pp. 180–184, 2010.
• A. Warbhe and R. Dharaskar, “An active approach based on independent component analysis for digital image forensics,” Int. J. Comput. Sci. Inf. Technol. (IJCSIT), vol. 6, no. 3, pp. 2201–2203, 2015.
• A.D. Warbhe, R.V. Dharaskar, and V.M. Thakare, “Computationally efficient digital image forensic method for image authentication,” Procedia Comput. Sci., vol. 85, pp. 464–470, 2016.
• Y. Zhang, J. Goh, L.L. Win ve V. Thing, “Image region forgery detection: A deep learning approach”, Cryptology and Information Security Series, vol. 14, pp. 1–11, 2016
• T.S. Gunawan, S.A.M. Hanafiah, M. Kartiwi, N. Ismail, N.F. Za’bah ve A.N. Nordin, “Development of photo forensics algorithm by detecting photoshop manipulation using error level analysis”, Indonesian Journal of Electrical Engineering and Computer Science, vol. 7, no. 1, pp. 131–137, 2017.
• I.B.K. Sudiatmika, A. Suryawan ve I.M. Sudarma, “Image forgery detection using error level analysis and deep learning”, TELKOMNIKA, cilt 17, sayı 3, ss. 657–664, 2019.
• H.C. Patel ve M.M. Patel, “Forgery frame detection from the video using error level analysis”, International Journal of Advanced Engineering Research and Development (IJAERD), vol. 6, pp. 242–247, 2015.
• M.M. Isaac ve M. Wilscy, “Image forgery detection based on Gabor wavelets and local phase quantization”, Procedia Computer Science, vol. 58, pp. 76–83, 2015.
• G.K. Birajdar ve V.H. Mankar, “Digital image forgery detection using passive techniques: A survey”, Digital Investigation, vol. 10, no. 3, pp. 226–245, 2013.
• A. Swaminathan, M. Wu ve K.R. Liu, “Nonintrusive component forensics of visual sensors using output images”, IEEE Transactions on Information Forensics and Security, vol. 2, pp. 91–106, 2007.
• H. Yao, M. Xu, T. Qiao, Y. Wu ve N. Zheng, “Image forgery detection and localization via a reliability fusion map”, Sensors, vol. 20, p. 6668, 2020.
• H. Pu, T. Huang, B. Weng, F. Ye ve C. Zhao, “Overcome the brightness and jitter noises in video inter-frame tampering detection”, Sensors, vol. 21, p. 3953, 2021.
• Y.K. Lin ve T.Y. Yen, “A meta-learning approach for few-shot face forgery segmentation and classification”, Sensors, vol. 23, p. 3647, 2023.
• P. Kakar ve N. Sudha, “Exposing postprocessed copy-paste forgeries through transform-invariant features”, IEEE Transactions on Information Forensics and Security, vol. 7, pp. 1018–1028, 2012.
• D. Singh, “An image forensic technique based on JPEG ghosts”, Multimedia Tools and Applications, cilt 82, ss. 1–17, 2023.
• Wang, J., Liu, G., Zhang, Z., Dai, Y., Wang, Z., "Fast and robust forensics for image region-duplication forgery," Acta Autom. Sin., vol. 35, pp. 1488–1495, 2009.
• S. Chandana, C.R. Nagarathna, A. Amrutha ve A. Jayasri, “Detection of image forgery using error level analysis”, in Proceedings of the 2024 International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), Bangalore, India, pp. 1–5, 2024.
• H. Farid, "Exposing digital forgeries from JPEG ghosts," IEEE Trans. Inf. Forensics Secur., vol. 4, no. 1, pp. 154–160, 2009.
• T.M. Geethanjali, T.S. Darshan, K. Surya, H.U. Rahul ve N.S. Ipshika, “Detecting image manipulation using error level analysis and convolutional neural networks on CASIA V2.0 dataset”, in Proceedings of the International Conference on Signal Processing, Computation, Electronics, Power, and Telecommunication, Mandya, India, pp. 20–25, 2024.
• R. Idlbek, M. Pešić ve K. Šolić, “Enhancing digital image forensics with error level analysis (ELA) and AI techniques”, in Proceedings of the 47th International MIPRO Convention on ICT and Electronics, Opatija, Croatia, pp. 1555–1560, 2024.
• I. Sudianto ve N. Anwar, “Image forensics using error level analysis and block matching methods”, Mobile and Forensics Journal, vol. 6, no. 2, pp. 1–11, 2024.
• H.T. Sencar ve N. Memon (Ed.), Digital Image Forensics, Springer, 2012.
• M.A. Qureshi ve M. Deriche, “A review on image forgery detection techniques”, Information Sciences, vol. 279, pp. 251–272, 2014.
• M.C. Stamm, M. Wu ve K.J.R. Liu, “Information forensics: An overview of the first decade”, IEEE Access, vol. 1, pp. 167–200, 2012.
• L. Nataraj, A. Elgammal, S. Hsu ve B.S. Manjunath, “Forgery detection in paintings using supervised learning”, in Proceedings of the 12th ACM Workshop on Multimedia Security, pp. 75–80, 2010.
• J. Chen, J. Ni, Y. Huang, Y. Huang ve C. Yang, “A deep learning based method for detecting image forgeries by identifying discriminative patch regions”, Neural Computing and Applications, vol. 30, no. 6, pp. 1865–1882, 2018.
• R. Salloum, Y. Ren, C.C.J. Kuo, "Image splicing localization using a multi-task fully convolutional network (MFCN)," J. Vis. Commun. Image Represent., vol. 51, pp. 201–209, 2018.
• J. Dong, W. Wang, T. Tan, Y.Q. Shi, "Run-length and edge statistics based approach for image splicing detection," IEEE Trans. Image Process., vol. 22, no. 12, pp. 4965–4977, 2013.
• N. Azhan, S. Abd Razak, I.R. Adeyemi, "Analysis of DQT and DHT in JPEG files," Int. J. Inf. Technol. Comput. Sci., vol. 10, pp. 1–11, 2013.
• M. Kirchner, J. Fridrich, "On detection of median filtering in digital images," Proc. SPIE, vol. 7541, 2010.
• Sophatvathana, "CASIA Dataset [CASIA2]," Kaggle, 2020. [Çevrimiçi].Erişim:https://www.kaggle.com/datasets/sophatvathana/casia-dataset?select=CASIA2.
• Columbia University, "Columbia Image Splicing Detection Evaluation Dataset," 2004. [Çevrimiçi]. Erişim: https://www.ee.columbia.edu/ln/dvmm/downloads/AuthSplicedDataSet/AuthSplicedDataSet.htm
• M. Patel, K. Rane, N. Jain, P. Mhatre ve S. Jaswal, “Image forgery detection using CNN”, in Proceedings of the 2023 3rd International Conference on Intelligent Technologies (CONIT), Hubli, India, pp. 1–4, 2023.
• J. Dong, W. Wang ve T. Tan, “CASIA image tampering detection evaluation database”, in Proceedings of the 2013 IEEE China Summit and International Conference on Signal and Information Processing, Beijing, China, pp. 422–426, 2013.
• S. Ng, J. Hsu, M. Pepeljugoski ve S. Chang, “Columbia photographic images and photorealistic computer graphics dataset”, 2005.