Metraipolis › archive › dc_b2602ba47b71
SAGEGAN: Style-Based Anomaly Detection with Gaussian Embeddings using Generative Adversarial Networks — arXiv:2609.27357
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.27357
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T10:13:11.209Z
- SHA-256 of the archived text
32f4cc7befe83ec6ba19893f3bb9b20d6ebe83d603ddc96996af328ed455b1fa- Stable URL of this page
https://metraipolis.com/documento/dc_b2602ba47b71
How to cite
SAGEGAN: Style-Based Anomaly Detection with Gaussian Embeddings using Generative Adversarial Networks — arXiv:2609.27357 — arXiv (en), https://arxiv.org/abs/2609.27357 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b2602ba47b71 (Metraipolis archive dc_b2602ba47b71, sha256 32f4cc7befe83ec6ba19893f3bb9b20d6ebe83d603ddc96996af328ed455b1fa)
BibTeX
@misc{dcb2602ba47b71,
title = {SAGEGAN: Style-Based Anomaly Detection with Gaussian Embeddings using Generative Adversarial Networks — arXiv:2609.27357},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.27357},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b2602ba47b71; sha256 32f4cc7befe83ec6ba19893f3bb9b20d6ebe83d603ddc96996af328ed455b1fa},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27357. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Malware evolves faster than rule-based and signature-driven detection pipelines. This paper presents SAGEGAN, a benign-only trained malware anomaly detection framework that converts portable executable files into compact three-channel images and models benign structure through style-conditioned adversarial reconstruction. The representation combines Hilbert-mapped byte values, benign-referenced byte-transition surprise, and entropy deviation from benign software. The model encodes each image into a layer-wise style tensor aligned with a seven-stage modulated generator, rather than a single latent bottleneck. A Gaussian style prior, moment-based prior alignment, and latent consistency are used to reduce mismatch between encoded benign styles and the generator's sampled manifold. For interpretation, a deterministic encoder pathway maps each executable to a fixed style tensor, enabling repeatable layer-wise family distance, gradient sensitivity, principal component, and class-behaviour analyses. On a self-collected portable executable corpus containing malware from 214 families, the Gaussian variant achieves 89.76% area under the receiver operating characteristic curve and 88.19% balanced accuracy, while the genome-style variant reaches 88.03% and 84.09%, respectively. Without refitting model weights, benign reference statistics, or decision thresholds, the same checkpoints are evaluated on DIKE, Microsoft BIG 2015, and Lester malware subsets. The results suggest that layer-wise style modelling supports both anomaly ranking and structured post hoc analysis of how malware families depart from the benign manifold. Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-24 in cs.CR). Categorie arXiv: Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2609.27357 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T09:26:35.692Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).