International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Advanced Approaches to Reverse Prompt Engineering in AI-Generated Content |
|---|---|
| ABSTRACT | The rapid advancement of generative Artificial Intelligence has significantly increased the creation of AI-generated digital content such as synthetic images and deepfakes. This has introduced major challenges in cyber security, digital forensics, and content authenticity verification. Conventional image analysis techniques often fail to accurately identify AI-generated content because modern generative models produce highly realistic outputs with minimal visible artifacts. This paper attempts to provide an advanced framework for Reverse Prompt Engineering and AI-generated image forensic analysis. The proposed system performs multimodal analysis using metadata inspection, forensic feature evaluation, AI probability estimation, and prompt reconstruction techniques. The framework analyzes uploaded images through integrated forensic modules such as EXIF metadata analysis, Error Level Analysis (ELA), FFT-inspired spectral analysis, and AI-assisted interpretation. The performance of the proposed system is analyzed based on forensic consistency, AI-generation probability, and reconstructed prompt estimation. The proposed system shows effective identification of synthetic media and improves digital forensic investigation capabilities through multimodal forensic analysis. |
| AUTHOR | HARISH KUMAR K, MAGNA Y, SANKARA NARAYANAN S T PG Student, Dept. of Cyber Security, Dr. MGR Educational and Research Institute, Chennai, India Assistant Professor, Dept. of Cyber Security, Dr. MGR Educational and Research Institute, Chennai, India Assistant Professor, Dept. of ISDF, Center of Excellence in Digital Forensics, Perungudi, Chennai, India |
| VOLUME | 185 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1406050 |
| pdf/50_Advanced Approaches to Reverse Prompt Engineering in AI-Generated Content.pdf | |
| KEYWORDS | |
| References | 1. Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville and Yoshua Bengio, “Generative Adversarial Networks”, Advances in Neural Information Processing Systems (NIPS), pp. 2672-2680, 2014. 2. Jonathan Ho, Ajay Jain and Pieter Abbeel, “Denoising Diffusion Probabilistic Models”, Advances in Neural Information Processing Systems (NeurIPS), Vol. 33, pp. 6840-6851, 2020. 3. Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser and Björn Ommer, “High-Resolution Image Synthesis with Latent Diffusion Models”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10684-10695, 2022. 4. Tero Karras, Samuli Laine and Timo Aila, “A Style-Based Generator Architecture for Generative Adversarial Networks”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4401-4410, 2019. 5. Hany Farid, “Image Forgery Detection”, IEEE Signal Processing Magazine, Vol. 26, Issue 2, pp. 16-25, 2009. 6. Matthew Stamm, Min Wu and K. J. Ray Liu, “Information Forensics: An Overview of the First Decade”, IEEE Access, Vol. 1, pp. 167-200, 2013. 7. David Cozzolino, Giovanni Poggi and Luisa Verdoliva, “Recasting Residual-based Local Descriptors as Convolutional Neural Networks: An Application to Image Forgery Detection”, ACM Workshop on Information Hiding and Multimedia Security, pp. 159-164, 2017. 8. Andreas Rossler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies and Matthias Nießner, “FaceForensics++: Learning to Detect Manipulated Facial Images”, IEEE International Conference on Computer Vision (ICCV), pp. 1-11, 2019. 9. Yue Wu, Wael Abd-Almageed and Prem Natarajan, “ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9543-9552, 2019. 10. Sarah Kreps, Miles McCain and Miles Brundage, “All the News That’s Fit to Fabricate: AI-Generated Text as a Tool of Media Misinformation”, Journal of Experimental Political Science, Vol. 9, Issue 1, pp. 104-117, 2022. 11. Yisroel Mirsky and Wenke Lee, “The Creation and Detection of Deepfakes: A Survey”, ACM Computing Surveys, Vol. 54, Issue 1, pp. 1-41, 2021. 12. Ning Yu, Larry Davis and Mario Fritz, “Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints”, IEEE International Conference on Computer Vision (ICCV), pp. 7556-7566, 2019. |
