EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Retrieval-Augmented Few-Shot Malware Detection via Binary Visualization and Vision–Language Embeddings

Woo Jin Jung, Nae-Joung Kwak, Byoung-Yup Lee

Applied Sciences · 22.04.2026 · 16 (9) · 4100

DOI: 10.3390/app16094100 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 22.04.2026. Verfasst von Woo Jin Jung und 2 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information & Communications Technology Planning & Evaluation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid evolution of malware families poses significant challenges for cybersecurity systems, particularly when newly emerging threats lack sufficient labeled data. Although image-based deep learning approaches have achieved strong performance under fully supervised conditions, their dependence on retraining limits adaptability in dynamic environments. To address this issue, we propose a Retrieval-Augmented Few-Shot Malware Detection Framework that integrates binary-to-image visualization, multimodal embedding using a frozen Vision–Language Model (Qwen2.5-VL), and similarity-based external memory retrieval. Malware binaries are converted into grayscale images and embedded into a semantic vector space without task-specific fine-tuning. During inference, query samples retrieve similar support embeddings from a vector database, and predictions are generated through similarity-weighted aggregation, enabling adaptation without parameter updates. Evaluated on the MalImg dataset with 25 malware families under 1-shot to 10-shot settings, the framework achieves 0.886 accuracy in the 10-shot configuration. Ablation results demonstrate that combining VLM embeddings with retrieval mechanisms provides consistent improvements over individual components. These findings highlight the effectiveness of decoupling representation learning from adaptation for scalable few-shot malware detection.

Förderung

  • Institute of Information & Communications Technology Planning & Evaluation

Zitieren

APA

Jung, W. J., Kwak, N., & Lee, B. (2026). Retrieval-Augmented Few-Shot Malware Detection via Binary Visualization and Vision–Language Embeddings. Applied Sciences, 16(9), 4100. https://doi.org/10.3390/app16094100

Vancouver

Jung WJ, Kwak N, Lee B. Retrieval-Augmented Few-Shot Malware Detection via Binary Visualization and Vision–Language Embeddings. Applied Sciences. 2026;16(9):4100. doi:10.3390/app16094100

BibTeX
@article{Jung2026,
  author = {Jung, Woo Jin and Kwak, Nae-Joung and Lee, Byoung-Yup},
  title = {Retrieval-Augmented Few-Shot Malware Detection via Binary Visualization and Vision–Language Embeddings},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {9},
  pages = {4100},
  doi = {10.3390/app16094100}
}
Kostenlos starten →