EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multimodal Malware Detection under Obfuscated and Adversarial Attack Conditions Using ResNet-50 and MLP Encoders with Contrastive Learning and Adaptive Cross-Modal Fusion

Peter Sackitey, Collinson Colin Mawunyo Agbesi, Timothy Graham

Applied Cybersecurity & Internet Governance · 19.05.2026

DOI: 10.60097/acig/219075 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Cybersecurity & Internet Governance, online erschienen am 19.05.2026. Verfasst von Peter Sackitey und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Traditional Android malware detection methods such as basic heuristic and signature-based methods as well as those trained on unimodal data samples are exposed to challenges from contemporary malware that utilizes advanced evasion techniques like adversarial and obfuscation perturbed variants to avoid detection. This work presents a multimodal malware detection method that uses image-based and tabular representations of Android APKs. A ResNet-50 network is used to extract visual embeddings from byteplot images that capture structural patterns resilient to obfuscated variants, while tabular data was analysed by a masked autoencoder pre-trained MLP to model behavioural correlations. An adaptive fusion technique dynamically weights the contributions of each modality per sample while Cross-modal contrastive learning aligns these embeddings in a shared latent space. The fused representation is fed into a supervised classifier to predict benign and malware categories. Adversarial, obfuscated, and clean scenarios confirmed outstanding results on tests samples from the multimodal CIC-MalDroid2020 dataset. Evaluation metrics include accuracy, recall, precision, F1-score, and macro-averaged receiver operating characteristic–area under the curve (ROC-AUC). Statistical significance is assessed using McNemar’s test. The results show that multimodal integration and adaptive fusion greatly improve detection generalization against evolving malware threats.

Zitieren

APA

Sackitey, P., Agbesi, C. C. M., & Graham, T. (2026). Multimodal Malware Detection under Obfuscated and Adversarial Attack Conditions Using ResNet-50 and MLP Encoders with Contrastive Learning and Adaptive Cross-Modal Fusion. Applied Cybersecurity & Internet Governance. https://doi.org/10.60097/acig/219075

Vancouver

Sackitey P, Agbesi CCM, Graham T. Multimodal Malware Detection under Obfuscated and Adversarial Attack Conditions Using ResNet-50 and MLP Encoders with Contrastive Learning and Adaptive Cross-Modal Fusion. Applied Cybersecurity & Internet Governance. 2026. doi:10.60097/acig/219075

BibTeX
@article{Sackitey2026,
  author = {Sackitey, Peter and Agbesi, Collinson Colin Mawunyo and Graham, Timothy},
  title = {Multimodal Malware Detection under Obfuscated and Adversarial Attack Conditions Using ResNet-50 and MLP Encoders with Contrastive Learning and Adaptive Cross-Modal Fusion},
  journal = {Applied Cybersecurity & Internet Governance},
  year = {2026},
  doi = {10.60097/acig/219075}
}
Kostenlos starten →