TY  - JOUR
AU  - Khan, Inam Ullah
AU  - Zeb, Asim
AU  - Rahman, Taj
AU  - Khan, Fida Muhammad
AU  - Haider, Zeeshan Ali
AU  - Bilal, Hazrat
PY  - 2025
DA  - 2025/03/31
TI  - ViTDroid and Hybrid Models for Effective Android and IoT Malware Detection
JO  - ICCK Transactions on Advanced Computing and Systems
T2  - ICCK Transactions on Advanced Computing and Systems
JF  - ICCK Transactions on Advanced Computing and Systems
VL  - 1
IS  - 1
SP  - 32
EP  - 47
DO  - 10.62762/TACS.2024.521915
UR  - https://www.icck.org/article/abs/TACS.2024.521915
KW  - Android malware
KW  - IoT malware
KW  - RNN
KW  - LSTM
KW  - GRU
KW  - ViTDroid
KW  - hybrid models
KW  - malware detection
KW  - deep learning
AB  - This paper introduces ViTDroid, a novel hybrid model that combines Vision Transformers (ViTs) and recurrent neural networks (RNNs) to enhance Android and IoT malware detection. ViTDroid addresses critical challenges by leveraging ViTs to capture global spatial dependencies and RNNs (LSTM and GRU) to model temporal patterns, enabling comprehensive analysis of complex malware behaviors. Additionally, the model integrates explainability tools, such as LIME and SHAP, to enhance transparency and trustworthiness, essential for real-world cybersecurity applications. The study evaluates ViTDroid's performance against conventional models, including RNN, LSTM, and GRU, using accuracy, precision, recall, and F1 score as evaluation metrics. Results demonstrate that ViTDroid achieves superior performance with an accuracy of 99.1% for Android malware and 98% for IoT malware. Precision and recall values reach 0.99 and 0.98, respectively, for Android, and 0.97 and 0.98 for IoT, with F1 scores of 0.99 for Android and 0.97 for IoT. These findings underscore ViTDroid's potential as a robust, efficient, and explainable solution to combat evolving threats in mobile and IoT ecosystems, paving the way for future advancements in malware detection systems.
SN  - 3068-7969
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Khan2025ViTDroid,
  author = {Inam Ullah Khan and Asim Zeb and Taj Rahman and Fida Muhammad Khan and Zeeshan Ali Haider and Hazrat Bilal},
  title = {ViTDroid and Hybrid Models for Effective Android and IoT Malware Detection},
  journal = {ICCK Transactions on Advanced Computing and Systems},
  year = {2025},
  volume = {1},
  number = {1},
  pages = {32-47},
  doi = {10.62762/TACS.2024.521915},
  url = {https://www.icck.org/article/abs/TACS.2024.521915},
  abstract = {This paper introduces ViTDroid, a novel hybrid model that combines Vision Transformers (ViTs) and recurrent neural networks (RNNs) to enhance Android and IoT malware detection. ViTDroid addresses critical challenges by leveraging ViTs to capture global spatial dependencies and RNNs (LSTM and GRU) to model temporal patterns, enabling comprehensive analysis of complex malware behaviors. Additionally, the model integrates explainability tools, such as LIME and SHAP, to enhance transparency and trustworthiness, essential for real-world cybersecurity applications. The study evaluates ViTDroid's performance against conventional models, including RNN, LSTM, and GRU, using accuracy, precision, recall, and F1 score as evaluation metrics. Results demonstrate that ViTDroid achieves superior performance with an accuracy of 99.1\% for Android malware and 98\% for IoT malware. Precision and recall values reach 0.99 and 0.98, respectively, for Android, and 0.97 and 0.98 for IoT, with F1 scores of 0.99 for Android and 0.97 for IoT. These findings underscore ViTDroid's potential as a robust, efficient, and explainable solution to combat evolving threats in mobile and IoT ecosystems, paving the way for future advancements in malware detection systems.},
  keywords = {Android malware, IoT malware, RNN, LSTM, GRU, ViTDroid, hybrid models, malware detection, deep learning},
  issn = {3068-7969},
  publisher = {Institute of Central Computation and Knowledge}
}