Citation :

Shaik Sharmila, Ch. Aparna, "DCA: A Residual CNN And Wireshark-Based Framework for Detecting Double JPEG Compression Anti-Forensic Attacks in Cloud Environments," International Journal of Electronics and Communication Engineering, vol. 13, no. 7, pp. 1-16, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I7P101

Abstract

Cloud computing brings integrity and reliability of digital images with a spectrogram of an anti-forensics method named as the double JPEG compression. These are meant to conceal the traces of intrusion which poses difficulties to the forensic analysts and investigators. In this direction, we come up with DCA (Detection and Classification Architecture), a hybrid and strong framework that does attack-resistant detection and localization of anti-forensic of the double JPEG compression. Network architecture incorporates the best capabilities of CNNs in extracting features and the Wireshark-based network traffic analysis, which provides improved traceability and validation. The CNN model can extract spatial and frequency domain inefficiency in image data that cannot be seen by a human eye but rather are recompression artifacts. Unlike conventional methods that rely solely on image-domain analysis, the proposed DCA introduces a dual-domain forensic strategy that integrates spatial–frequency feature learning with network-level traffic monitoring, enabling both content-based and transmission-aware verification of image authenticity. Meanwhile, it monitors transmission patterns in Wireshark to monitor the spread of images that were manipulated, and where it all goes amiss. The outputs of the system include binary classification (tampered/ untampered) and heatmaps to overlay on the input images to show the suspicious areas. To test the quality of DCA, we tested DCA on emphasized performance measures: Precision, Accuracy, True Positive Rate (TPR), False Positive Rate (FPR), F-score, Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index Measure (SSIM). Experimental evidence indicates that DCA is interpretably stable with high detectability. The main input of the work is the creation of a coherent multi-domain forensic model that combines the residual CNN-based spatial frequency feature extraction with network traffic analysis Wireshark. The proposed DCA framework can detect and trace multiple tampering of images simultaneously compared to the conventional techniques that use single-domain analysis, leading to better accuracy, robustness, and reliability when using same-quantization double JPEG compression configurations. The framework also offers classification as well as localization results and is best suited to the real-time cloud forensic investigations.

Keywords

Anti-forensic detection, Cloud forensics, Convolutional Neural Network, Double JPEG compression, Image tampering.

References

1. Dong-Hoon Kwak et al., “Sub-Terahertz Imaging-Based Real-Time Non-Destructive Inspection System for Estimating Water Activity and Foreign Matter Depth in Seaweed,” Sensors, vol. 24, no. 23, pp. 1-19, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
2. Yiming Deng, and Xin Liu, “Electromagnetic Imaging Methods for Nondestructive Evaluation Applications,” Sensors, vol. 11, no. 12, pp. 11774-11808, 2011.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Xiuwei Yang et al., “Defect Detection of Composite Material Terahertz Image Based on Faster Region-Convolutional Neural Networks,” Materials, vol. 16, no. 1, pp. 1-14, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Ramesh Kumpati, Wojciech Skarka, and Sunith Kumar Ontipuli, “Current Trends in Integration of Nondestructive Testing Methods for Engineered Materials Testing,” Sensors, vol. 21, no. 18, pp. 1-32, 2021.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Kirsti Krügener et al., “Terahertz Inspection of Buildings and Architectural Art,” Applied Sciences, vol. 10, no. 15, pp. 1-17, 2020.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Marco Civera, and Cecilia Surace, “Non-Destructive Techniques for the Condition and Structural Health Monitoring of Wind Turbines: A Literature Review of the Last 20 Years,” Sensors, vol. 22, no. 4, pp. 1-52, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Zhang Yue et al., “Single-Shot Direct Transmission Terahertz Imaging Based on Intense Broadband Terahertz Radiation,” Sensors, vol. 24, no. 13, pp. 1-12, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Weiyi Wei et al., “JAMD-Net: Image Splicing Forgery Detection based on JPEG Compression Artifacts and Multi-Dilated Channel Refinement Fusion,” Multimedia Systems, vol. 32, 2026.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Wenqi Zhao, Zhenjiang Li, and Lixin Wang. “Document Image Tampering Detection and Location Based on Multi-Scale Feature Fusion,” Engineering Research Express, vol. 8, no. 7, 2026.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Long Zhuo et al., “Evading Detection Actively: Toward Anti-Forensics against Forgery Localization,” IEEE Transactions on Dependable and Secure Computing, vol. 22, no. 2, pp. 852-869, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Patchara Sutthiwan, and Yun Q. Shi, “Anti-Forensics of Double JPEG Compression Detection,” Digital Forensics and Watermarking, pp. 411-424, 2012.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Haodong Li, Weiqi Luo, and Jiwu Huang, “Anti-Forensics of Double JPEG Compression with the Same Quantization Matrix,” Multimedia Tools and Applications, vol. 74, pp. 6729-6744, 2015.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Kutub Uddin, Yoonmo Yang, and Byung Tae Oh, “Anti-Forensic Against Double JPEG Compression Detection using Adversarial Generative Network,” Proceedings of the Korean Society of Broadcasting and Media Engineers Conference, pp. 58-60, 2019.
    [Google Scholar]
14. Weixuan Tang, Dequ Huang, and Bin Li, “Anti‐Forensics for Double JPEG Compression based on Deep Reinforcement Learning, Electronics Letters, vol. 58, no. 25, pp. 969-971, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
15. Tomas Pevny, and Jessica Fridrich, “Detection of Double-Compression in JPEG Images for Applications in Steganography,” IEEE Transactions on Information Forensics and Security, vol. 3, no. 2, pp. 247-258, 2008.
    [CrossRef] [Google Scholar] [Publisher Link]
16. M. Barni et al., “Aligned and Non-Aligned Double JPEG Detection Using Convolutional Neural Networks,” Journal of Visual Communication and Image Representation, vol. 49, pp. 153-163, 2017.
    [CrossRef] [Google Scholar] [Publisher Link]
17. Pengpeng Yang, Rongrong Ni, and Yao Zhao, “Double JPEG Compression Detection by Exploring the Correlations in DCT Domain,” 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Honolulu, HI, USA, pp. 728-732, 2018.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Bin Li et al., “A Multi-Branch Convolutional Neural Network for Detecting Double JPEG Compression,” arXiv preprint, pp. 1-16, 2017.
    [CrossRef] [Google Scholar] [Publisher Link]
19. Feng Ding et al., “ExS-GAN: Synthesizing Anti-Forensics Images via Extra Supervised GAN,” IEEE Transactions on Cybernetics, vol. 53, no. 11, pp. 7162-7175, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
20. Dohyun Kim, Wonhyuk Ahn, and Heung-Kyu Lee, “End-to-End Anti-Forensics Network of Single and Double JPEG Detection,” IEEE Access, vol. 9, pp. 13389-13401, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
21. Haitao Zhang et al., “A Local Perturbation Generation Method for GAN-Generated Face Anti-Forensics,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 33, no. 2, pp. 661-675, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
22. Xiang Feng et al., “Anti-Forensics for JPEG Decompression Based on Generative Adversarial Network,” 2024 5^th International Conference on Computer Engineering and Application (ICCEA), Hangzhou, China, pp. 63-66, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]