Searcharxiv⌕ Search

arXiv subjects

Noor Abo Hasan

Publications and source records attributed to Noor Abo Hasan.

2 recordsLinked to original sources

A Forensic Analysis of Metadata and Information Leakage in Swedish Public Documents

This study investigates metadata and structural content leakage in publicly available PDF documents from 30 Swedish public-sector authorities. Using an automated collection pipeline and ExifTool-based extraction, 2,876 documents were analyzed and classified using an R0-R3 risk taxonomy. Results reveal that 48.4% of documents exhibit significant metadata exposure (R2 or R3), with significant variation across institutional tiers (p < 0.001). Longitudinal analysis across three legislative periods reveals a statistically significant reduction in metadata exposure between the baseline and post-enactment periods, yet 44.9% of documents published after the enactment of the Swedish Cybersäkerhetslagen continue to leak sensitive metadata. Furthermore, 41.6% of documents contain incremental update layers; forensic analysis recovered verifiable text alterations, including deleted personal data and internal identifiers, from 228 of these cases. These findings highlight persistent regulatory lag and a systemic reliance on default, unsanitized document publication workflows within the Swedish public sector.

cs.CR↗

CNN Architecture Comparison for Malware Classification with Limited Training Data

Traditional malware classification methods struggle to keep pace with rapidly evolving threats. Image-based malware classification offers a promising alternative by converting malware binaries into grayscale images for analysis with deep learning. While effective, organizations often face practical constraints in acquiring sufficient training data, especially for newer threats. This thesis investigates dual-path CNN architectures with intermediate feature fusion as a potential enhancement for malware classification, with particular focus on how varying training data size affects their comparative performance against traditional single-path approaches. This research implements and compares two models: a baseline single-path using the pre-trained VGG16 architecture and a dual-path model that combines VGG16 with a custom CNN through intermediate feature fusion. Both architectures are evaluated on a binary classification task distinguishing between two malware families (C2Lop.P trojan and Dialplatform.B worm) from the Malimg dataset. Each model is trained across four different training data proportions (20%, 40%, 60%, and 80%), with three training runs per size to ensure statistical robustness, while being evaluated on complementary test sets of varying sizes. Though both architectures achieved perfect classification performance across all training percentages, the study revealed significant differences in secondary metrics including training efficiency, robustness to noise perturbation, and architectural complexity. The findings challenge common assumptions about complex architectures, demonstrating that simpler models can offer superior efficiency and robustness without sacrificing classification performance in image-based malware analysis.

cs.CR↗