Architected Graph-Enhanced Neural Network Framework for Image Integrity and Tamper Precision

Jafarizade, Khashayar; Majidi, Mohammad Hassan; Gholamalinejad, Hossein

doi:10.22042/isecure.2026.242096

Architected Graph-Enhanced Neural Network Framework for Image Integrity and Tamper Precision

Articles in Press

Document Type : Research Article

Authors

Khashayar Jafarizade ¹

Mohammad Hassan Majidi ¹

Hossein Gholamalinejad ²

¹ Faculty of Electrical and Computer Engineering, University of Birjand, Birjand, Iran.

² Department of Computer Engineering, Bozorgmehr University of Qaenat, Qaenat, Iran.

10.22042/isecure.2026.242096

Abstract

Image authenticity is a perennial issue with the evolution of advanced tampering techniques, particularly grid-aligned manipulations and spatial vulnerability-exploiting post-processing attacks. The paper presents a novel architecture for a neural network fusing Graph Neural Networks (GNNs), Convolutional Neural Networks (CNNs), and digital watermarking to detect tampering successfully and localise it. CNNs are trained on learning local spatial features, and an invisible low-dropout convolutional encoder places watermarks to ensure authenticity. GNNs address the inherent problem of modelling long-range structural relations for blind tampering pattern detection that is accurate. With a graph-based representation of image blocks, the framework learns complex spatial relations, which alleviates the rigid receptive field limitation. Extensive experiments on benchmark datasets confirm the framework’s superiority, achieving an F1-Score of 0.94 in tampering localisation, which significantly outperforms the 0.88 F1-Score of leading state-of-the-art methods. This approach creates a new standard for image integrity verification, offering an interpretable and scalable solution with far-reaching applications in digital content protection.

Keywords

Authenticity Protection

Digital Manipulation

Graph Representation

Spatial Analysis

Tamper Detection

[1] An-Sofie Shrestha, Kate Moore, and Prawesh P. Paudyal. Self-Image Manipulation on Social Media: A Survey of User Motivations and Practices. Social Media + Society, 7(3), 2021.

[2] H. Farid. Image forgery detection. IEEE Signal Processing Magazine, 26(2):16–25, Mar 2009.

[3] J. Fridrich. Methods for tamper detection in digital images. Proc. ACM Workshop Multimedia Security, pages 19–23, 2002.

[4] C.-Y. Lin and S.-F. Chang. A robust image authentication method. IEEE Transactions on Image Processing, 27(5):2304–2315, May 2018.

[5] E. Walia and A. Jain. An analysis of lsb based image steganography techniques. Procedia Computer Science, 48:619–624, 2015.

[6] A. C. Popescu and H. Farid. Exposing digital forgeries by detecting traces of resampling. IEEE Transactions on Signal Processing, 53(2): 758–767, Feb 2005.

[7] W. Zhang et al. Cnn-based jpeg anti-forensics detection. Proc. IEEE International Conference on Image Processing, pages 345–350, 2023.

[8] J. H. Bappy et al. Hybrid lstm and cnn for image forgery detection. IEEE Transactions on Information Forensics and Security, 12(10):2345– 2356, Oct 2017.

[9] X. Wang et al. Gnn for structural tampering detection. IEEE Transactions on Multimedia, 26:5678–5689, 2024.

[10] Q. Li et al. Multi-attack vulnerability in image forensics pipelines. IEEE Transactions on Dependable and Secure Computing, 2025. Early Access.

[11] P. Sharma et al. Noiseprint: An attack-agnostic forensic technique. IEEE Transactions on Information Forensics and Security, 18:789–800, 2023.

[12] B. Mahdian and S. Saic. Using noise inconsistencies for blind image forensics. Image and Vision Computing, 27(10):1497–1503, 2009.

[13] A. Gupta et al. Graph attention networks for media forensics. IEEE Transactions on Multimedia, 26:7890–7901, 2024.

[14] H. Zhang et al. Multi-scale feature integration with gnns. IEEE Transactions on Image Processing, 32:456–467, 2023.

[15] Zhaofeng Wu, Qichao Zhu, Xiaobing Kang, and Siwei Lyu. MANet: A new perspective for image tampering detection. In Proceedings of the 30th ACM International Conference on Multimedia, pages 1331–1340. ACM, 2022.

[16] W. Chen et al. Transformer-based detection of scaling operations. Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11245–11254, 2024.

[17] Casia image tampering detection dataset. Available: http://www.casia.ac.cn/, 2023.

[18] Nist nimble challenge dataset. Available: https://www.nist.gov/, 2024.

[19] Y. Lu et al. Attention-based cnn for image tampering detection. IEEE Access, 11:12345–12356, 2023.

[20] M. Islam et al. Explainable ai in image forensics. Journal of Visual Communication and Image Representation, 89:103678, 2023.

[21] M. Billah. Developing an Explainable AI System for Digital Forensics: Enhancing Trust and Transparency in Flagging Events for Legal Evidence. Journal of Forensic Science Research, 9 (2):109–116, 2025.

[22] Z. Qin et al. Graphformer: Combining transformers with gnns. IEEE Transactions on Neural Networks and Learning Systems, 2024. Early Access.

[23] O. Iuzvyk et al. Universal detectors for postprocessing attacks. IEEE Transactions on Information Forensics and Security, 19:4567–4578, 2024.

[24] O. Ronneberger et al. DF-Net: The Digital Forensics Network for Image Forgery Detection, 2025.

[25] T. Christ and L. Gunn. Undetectable and Robust Watermarking for Diffusion Models, 2025.

[26] P. Veliˇckovi´c et al. Graph attention networks. Proc. International Conference on Learning Representations, 2018.

[27] A. Kazi et al. Graph diffusion for anomaly detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(3):3456–3467, Mar 2023.

[28] A. Hore and D. Ziou. Image quality metrics: Psnr vs. ssim. Pattern Recognition, 43(8):1478– 1486, 2010.

[29] Z. Wang et al. Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4):600–612, Apr 2004.

[30] D. M. W. Powers. Evaluation: From precision, recall and f-measure to roc, informedness, markedness and correlation. Journal of Machine Learning Technology, 2(1):37–63, 2011.

[31] A. P. Bradley. The use of the area under the roc curve in the evaluation of machine learning algorithms. Pattern Recognition, 30(7):1145–1159, 1997.

[32] Q. Li et al. Advanced attack simulation in image forensics. IEEE Transactions on Information Forensics and Security, 19:3456–3467, 2024.