Digital forensic investigations often face significant challenges when recovering fragmented multimedia files that lack file system metadata. While traditional file carving relies on signatures and discriminative deep learning models for fragment classification, these methods cannot reconstruct or predict missing data. We propose a generative approach to multimedia carving using bGPT, a byte-level transformer designed for next-byte prediction. By feeding partial BMP image data into the model, we simulate the generation of likely fragment continuations. We evaluate the fidelity of these predictions using different metrics, namely, cosine similarity, structural similarity index (SSIM), chi-square distance, and Jensen-Shannon divergence (JSD). Our findings demonstrate that generative models can effectively predict byte-level patterns to support fragment matching in unallocated disk space.
@article{arxiv.2604.11010,
title = {Byte-level generative predictions for forensics multimedia carving},
author = {Jaewon Lee and Md Eimran Hossain Eimon and Avinash Srinivasan and Hari Kalva},
journal= {arXiv preprint arXiv:2604.11010},
year = {2026}
}
Comments
Accepted for publication at the "SPIE Defense + Security" Conference