Zero-Day Threat Mitigation via Deep Learning in Cloud Environments
Source abstract
Abstract
The growing sophistication of cyber threats has increased the need for advanced detection techniques, particularly in cloud computing environments. Zero-day threats pose a critical risk due to their ability to bypass traditional security mechanisms. This study proposes a deep learning model called mixed vision transformer (MVT), which converts binary files into images and applies deep attention mechanisms for classification. The model was trained using the MaLeX dataset in a simulated Docker environment. It achieved an accuracy between 70% and 80%, with better performance in detecting malware compared with benign files. The proposed MVT approach not only demonstrates its potential to significantly enhance zero-day threat detection in cloud environments but also sets a foundation for robust and adaptive solutions to emerging cybersecurity challenges.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Malware Detection Techniques · Network Security and Intrusion Detection · Anomaly Detection Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Escuela de Ingeniería Informática, Pontificia Universidad Católica de Valparaíso, Valparaíso 2340025, Chile
Knowledge Discovery, Fraunhofer-Institute of Intelligent Analysis and Information Systems (IAIS), 53757 Sankt Augustin, Germany
Lamarr Institute for Machine Learning and Artificial Intelligence, 44227 Dortmund, Germany
References (46)
Show source-provided references
1. Vanickis, R., Jacob, P., Dehghanzadeh, S., and Lee, B. (2018, January 21–22). Access control policy enforcement for zero-trust-networking. Proceedings of the 2018 29th Irish Signals and Systems Conference (ISSC), Belfast, UK.10.1109/ISSC.2018.8585365 ↗
2. Future industry internet of things with zero-trust security10.1007/s10796-021-10199-5 ↗
3. Detection of ransomware using machine learning techniques
4. Machine learning for cloud security: A systematic review10.1109/ACCESS.2021.3054129 ↗
5. Abdulsalam, Y.S., and Hedabou, M. (2022). Security and privacy in cloud computing: Technical review. Future Internet, 14.10.3390/fi14010011 ↗
6. Tyler, D., and Viana, T. (2021). Trust No One? A Framework for Assisting Healthcare Organisations in Transitioning to a Zero-Trust Network Architecture. Appl. Sci., 11.10.3390/app11167499 ↗
7. Augmenting Zero Trust Network Architecture to enhance security in virtual power plants10.1016/j.egyr.2021.11.272 ↗
8. Fileless malware threats: Recent advances, analysis approach through memory forensics and research challenges10.1016/j.eswa.2022.119133 ↗
9. Feng, T., and Akhtar, M.S. (2022). Malware analysis and detection using machine learning algorithms. Symmetry, 14.10.3390/sym14112304 ↗
10. Akhtar, M.S., and Feng, T. (2023). Evaluation of machine learning algorithms for malware detection. Sensors, 23.10.3390/s23020946 ↗
11. Alwaheidi, M.K.S., and Islam, S. (2022). Data-driven threat analysis for ensuring security in cloud enabled systems. Sensors, 22.10.3390/s22155726 ↗
12. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021, January 3–7). An image is worth 16x16 words: Transformers for image recognition at scale. Proceedings of the International Conference on Learning Representations (ICLR), Vienna, Austria.
13. Ullah, F., Alsirhani, A., Alshahrani, M., Alomari, A., Naeem, H., and Shah, S. (2022). Explainable malware detection system using transformers-based transfer learning and multi-model visual representation. Sensors, 22.10.3390/s22186766 ↗
14. Image-based malware representation approach with EfficientNet convolutional neural networks for effective malware classification
15. Functionality-preserving adversarial machine learning for robust classification in cybersecurity and intrusion detection domains: A survey10.3390/jcp2010010 ↗
16. (2025, March 08). Mayachitra, Inc. MaLeX: Malware Executable Dataset. Proceedings of the 54th Hawaii International Conference on System Sciences, Available online: https://github.com/Mayachitra-Inc/MaleX.
17. Nagy, N., Aljabri, M., Shaahid, A., Ahmed, A.A., Alnasser, F., Almakramy, L., Alhadab, M., and Alfaddagh, S. (2023). Phishing URLs detection using sequential and parallel ML techniques: Comparative analysis. Sensors, 23.10.3390/s23073467 ↗
18. Toward a zero trust architecture implementation in a university environment
19. Zero trust architecture: Trend and impact on information security10.46338/ijetae0722_15 ↗
20. Security and trust model analysis for banking system
21. Lukaseder, T., Halter, M., and Kargl, F. (2020). Context-based Access Control and Trust Scores in Zero Trust Campus Networks. Lecture Notes in Informatics, Gesellschaft für Informatik eV.
22. Efficientnet convolutional neural networks-based android malware detection
23. Kumar, R., and Subbiah, G. (2022). Zero-day malware detection and effective malware analysis using shapley ensemble boosting and bagging approach. Sensors, 22.10.3390/s22072798 ↗
24. Zero-day ransomware attack detection using deep contractive autoencoder and voting based ensemble classifier10.1007/s10489-022-03244-6 ↗
25. SMOTE: Synthetic minority over-sampling technique10.1613/jair.953 ↗
26. Lin, T., Lu, Y.K., Hu, J., and Zhou, Z. (2020, January 20). Improved K-Means Algorithm on Home Industry Data Clustering in the Province of Bangka Belitung. Proceedings of the 2020 International Conference on Smart Technology and Applications (ICoSTA), Surabaya, Indonesia. Available online: https://ieeexplore.ieee.org/document/9079313.
27. Multiclass malware classification using stacked ensemble learning based on static and dynamic features
28. Malware family classification based on file relations and graph embedding
29. Lundberg, S.M., and Lee, S.I. (2017). A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst., 30.
30. Explainable AI for cybersecurity: State-of-the-art, challenges and research directions
31. Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13–17). “Why should I trust you?”: Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939778 ↗
32. Ransomware: Attack, human impact and mitigation
33. Selfsupervised vision transformers for malware detection10.1109/ACCESS.2022.3206445 ↗
34. A novel deep learning-based approach for malware detection10.1016/j.engappai.2023.106030 ↗
35. Nataraj, L., Karthikeyan, S., Jacob, G., and Manjunath, B.S. (2011, January 20). Malware images: Visualization and automatic classification. Proceedings of the 8th International Symposium on Visualization for Cyber Security (VizSec), Pittsburgh, PA, USA.10.1145/2016904.2016908 ↗
36. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv.
37. Li, L., Jamieson, K., DeSalvo, G., Rostamizadeh, A., and Talwalkar, A. (2017, January 24–26). Hyperband: A novel bandit-based approach to hyperparameter optimization. Proceedings of the International Conference on Learning Representations (ICLR), Toulon, France.
38. Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges10.1002/widm.1484 ↗
39. Hussein, B.M., and Shareef, S.M. (2024, January 20–21). An Empirical Study on the Correlation between Early Stopping Patience and Epochs in Deep Learning. Proceedings of the ITM Web of Conferences, ICACS24, Erbil, Iraq.10.1051/itmconf/20246401003 ↗
40. Goal-Oriented Sensitivity Analysis of Hyperparameters in Deep Learning10.1007/s10915-022-02083-4 ↗
41. Cloud computing security and deep learning: An ann approach10.1016/j.procs.2023.12.155 ↗
42. Al-Canaan, A. (2019). Telecommunications Protocols Fundamentals, IntechOpen eBooks.10.5772/intechopen.86338 ↗
43. Jakhotiya, P., Khatri, A., and Buduru, A.B. (2022, January 16–18). Adversarial Attacks on Transformers-Based Malware Detectors. Proceedings of the 2022 International Conference on Cyber Security and Protection of Digital Services (Cyber Security), Hangzhou, China.
44. Li, Y., Hu, H., and Salem, A. (November, January 30). The Efficacy of Transformer-based Adversarial Attacks in Security Domains. Proceedings of the 2023 IEEE Military Communications Conference (MILCOM), Boston, MA, USA.10.1109/MILCOM58377.2023.10356372 ↗
45. How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses
46. Li, S., Chen, Y., and Zhang, X. (2023). PAD: Principled Adversarial Malware Detection Against Evasion Attacks. arXiv.