EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TL-RL-FusionNet: Reinforcement Learning-Guided Residual MLP with Fused CNN Embeddings for Efficient and Adaptive Ransomware Detection

Jannatul Ferdous iD, Rafiqul Islam iD, Arash Mahboubi iD, Md Zahidul Islam

Sensors · 27.07.2026 · 26 (15) · 4775

DOI: 10.3390/s26154775 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 27.07.2026. Verfasst von Jannatul Ferdous und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computing, Mathematics and Engineering, Charles Sturt University, Wagga Wagga, NSW 2650, Australia. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ransomware detection remains challenging because modern variants exhibit diverse, elusive, and partly benign behaviors and can propagate rapidly across interconnected enterprises and sensor-enabled cyber-physical systems, causing cascading operational failures. These characteristics undermine signature-based and static-detection methods. Although machine learning has improved detection, many approaches still rely on fixed objectives that weight samples uniformly, limiting their adaptation to heterogeneity and overlaps between ransomware and benign activities. To address this challenge, we introduce TL-RL-FusionNet, a reinforcement learning (RL)-guided hybrid framework that combines dual transfer learning (TL) backbones, EfficientNetB0 and InceptionV3, with a lightweight residual multi-Layer perceptron (MLP) classifier. The framework converts sandbox reports into RGB grids, extracts features using frozen CNN backbone networks, and fuses embeddings for classification. Training is guided by a tabular Q-learning sample-weighting agent, formulated as a per-sample bandit over discrete weight actions. To prevent cross-fold information leakage, the Q-table is freshly initialized in each cross-validation fold and updated only using the fold-local training partition, whereas the held-out fold is used for the final evaluation. The framework was evaluated using two datasets. On our dataset, TL-RL-FusionNet achieved the best overall performance on Dataset 1, with 99.20% accuracy, 99.40% recall, and 99.84% AUC. On the public EldeRan benchmark, it achieved 90.36% accuracy using the full dynamic feature space and 92.08% using a Mutual Information-selected compact subset. Paired Wilcoxon tests across five folds were used to assess the RL contribution, while additional grid-order sensitivity analysis showed that the image-based representation remained robust under five random 10 × 10 feature-grid permutations. Interpretability analysis using t-distributed stochastic neighbor embedding (t-SNE) and gradient-weighted class activation mapping feature-grid mapping further showed that the model captured discriminative behavioral patterns. Overall, these results demonstrate that RL-guided sample reweighting improves adaptive ransomware detection while maintaining efficiency and interpretability. The dataset and supporting code are publicly available on GitHub.

Schlagwörter

Stichwörter der Autor:innen

EfficientNetInceptionV3MLPQ-learningcybersecurityinterpretabilitymulti-CNN feature fusionransomware detectionreinforcement learningsample weightingsensor networkstransfer learning

Autor:innen und Institutionen

  • School of Computing, Mathematics and Engineering, Charles Sturt University, Wagga Wagga, NSW 2650, Australia.
  • School of Computing, Mathematics and Engineering, Charles Sturt University, Albury, NSW 2640, Australia.
  • School of Professional Studies, University of New South Wales (UNSW), Canberra, ACT 2600, Australia.
  • School of Computing, Mathematics and Engineering, Charles Sturt University, Bathurst, NSW 2795, Australia.
  • AI and Cyber Futures Center, Charles Sturt University, Panorama Avenue, Bathurst, NSW 2795, Australia.

ORCID-Profile: Jannatul Ferdous, Rafiqul Islam, Arash Mahboubi

Zitieren

APA

Ferdous, J., Islam, R., Mahboubi, A., & Islam, M. Z. (2026). TL-RL-FusionNet: Reinforcement Learning-Guided Residual MLP with Fused CNN Embeddings for Efficient and Adaptive Ransomware Detection. Sensors, 26(15), 4775. https://doi.org/10.3390/s26154775

Vancouver

Ferdous J, Islam R, Mahboubi A, Islam MZ. TL-RL-FusionNet: Reinforcement Learning-Guided Residual MLP with Fused CNN Embeddings for Efficient and Adaptive Ransomware Detection. Sensors. 2026;26(15):4775. doi:10.3390/s26154775

BibTeX
@article{Ferdous2026,
  author = {Ferdous, Jannatul and Islam, Rafiqul and Mahboubi, Arash and Islam, Md Zahidul},
  title = {TL-RL-FusionNet: Reinforcement Learning-Guided Residual MLP with Fused CNN Embeddings for Efficient and Adaptive Ransomware Detection},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {15},
  pages = {4775},
  doi = {10.3390/s26154775}
}
Kostenlos starten →