IJSDIP | International Journal of System Design & Info Processing

AI-Powered Cybersecurity Framework for Cloud-Based Applications: Enhancing malware detection and threat response using deep learning

Paper ID:

IJSDIP_2025_VOLUME 13_ISSUE 4_109-116

Author's Name:

Mr. Sathish Krishna Anumula

Volume:

Issue:

Issue 4

Year:

2025

Pages:

109-116

Abstract

Cloud-based applications are now core to the digital ecosystem modernity, yet due to their distributed nature and increasing attack surface, they are extremely exposed to high-tech cyber threats. The conventional security systems, including signature-based firewall and rule-based models that are always static, find it hard to detect zero-day attacks, polymorphic malware and dynamic threat behavior. The proposed paper suggests an AI driven cybersecurity system that incorporates deep learning in malware detection, anomaly detection, and in automated threat detection in cloud system. The framework uses convolutional neural networks (CNNs), recurrent neural networks (RNNs), and autoencoders to acquire the complex malware patterns and identify anomalies in the behavior of a system in real time. Experimental assessments indicate an increase in detection accuracy, low incident of false positives and quicker reacting to incidents as compared to traditional security tools. The results have shown that deep learning integration has a major role in ensuring security resilience against cloud-based architectures. The limitations in practice are the large, clean datasets required, the high computational cost and the possibility of adversarial attacks of the AI models. The future directions include federated learning, lightweight DL models on resource constrained clouds and explainable AI methods to enhance security transparency and trust.

Keywords

AI Security, Deep Learning, Cloud Computing, Malware Detection, Threat Response, Cybersecurity Framework, Anomaly Detection, Automated Defense.

References

[1] Y. Khan and M. Tufail, “AI-Driven Modern Cybersecurity Approach: A Systematic Literature review,” in Information systems engineering and management, 2025, pp. 1–14. doi: 10.1007/978-3-031-81481-5_1. [2] L. Albshaier, S. Almarri, and A. Albuali, “Federated Learning for Cloud and Edge Security: A Systematic Review of Challenges and AI opportunities,” Electronics, vol. 14, no. 5, p. 1019, Mar. 2025, doi: 10.3390/electronics14051019. [3] J. Trivedi, M. Tahir, and J. Isoaho, “AI-Enhanced Threat Intelligence in Remote Patient Monitoring Systems: A survey on recent advances, challenges and future research directions,” IEEE Access, vol. 13, pp. 106465–106488, Jan. 2025, doi: 10.1109/access.2025.3572626. [4] M. Almutairi and F. T. Sheldon, “IoT–Cloud Integration Security: A survey of challenges, solutions, and directions,” Electronics, vol. 14, no. 7, p. 1394, Mar. 2025, doi: 10.3390/electronics14071394. [5] Y. Harrath, O. Adohinzin, J. Kaabi, and M. Saathoff, “Bridging domains: Advances in Explainable, Automated, and Privacy-Preserving AI for computer science and cybersecurity,” Computers, vol. 14, no. 9, p. 374, Sep. 2025, doi: 10.3390/computers14090374. [6] M. A. Mohammed, S. A. Amir, and H. K. Hoomod, “Enhancing Blockchain Security: A survey on applications, threat mitigation, and an AI-Driven framework for IoT protection,” in Lecture notes in networks and systems, 2025, pp. 441–450. doi: 10.1007/978-3-032-02831-0_35. [7] E. Dritsas and M. Trigka, “A survey on the applications of cloud computing in the industrial internet of things,” Big Data and Cognitive Computing, vol. 9, no. 2, p. 44, Feb. 2025, doi: 10.3390/bdcc9020044. [8] Z. Elgammal, M. T. Albrijawi, and R. Alhajj, “Digital twins in healthcare: a review of AI-powered practical applications across health domains,” Journal of Big Data, vol. 12, no. 1, Oct. 2025, doi: 10.1186/s40537-025-01280-w. [9] E. Mardanov, I. Mavlutova, and B. Sloka, “AI-Powered Predictive Maintenance in oil and Gas: Maximizing efficiency and profitability,” in Lecture notes in networks and systems, 2025, pp. 496–511. doi: 10.1007/978-3-032-07989-3_32. [10] D. Puthal, A. K. Mishra, S. P. Mohanty, A. Longo, and C. Y. Yeun, “Shadow AI: Cyber security Implications, opportunities and challenges in the Unseen Frontier,” SN Computer Science, vol. 6, no. 5, Apr. 2025, doi: 10.1007/s42979-025-03962-x. [11] B. Amangeldyet al., “AI-Powered Building Ecosystems: A narrative mapping review on the integration of digital twins and LLMs for proactive comfort, IEQ, and energy management,” Sensors, vol. 25, no. 17, p. 5265, Aug. 2025, doi: 10.3390/s25175265. [12] D. Xu, I. Gondal, X. Yi, T. Susnjak, P. Watters, and T. R. McIntosh, “The Erosion of Cybersecurity Zero-Trust Principles through Generative AI: A survey on the challenges and future directions,” Journal of Cybersecurity and Privacy, vol. 5, no. 4, p. 87, Oct. 2025, doi: 10.3390/jcp5040087. [13] T. Miller, I. Durlik, E. Kostecka, S. Sokołowska, P. Kozlovska, and R. Zwolak, “Artificial Intelligence in Maritime Cybersecurity: A Systematic Review of AI-Driven Threat Detection and Risk Mitigation Strategies,” Electronics, vol. 14, no. 9, p. 1844, Apr. 2025, doi: 10.3390/electronics14091844. [14] L. Xi, C. Li, M. S. Anari, and K. Rezaee, “Integrating wearable health devices with AI and edge computing for personalized rehabilitation,” Journal of Cloud Computing Advances Systems and Applications, vol. 14, no. 1, Nov. 2025, doi: 10.1186/s13677-025-00795-0. [15] Whig, V. Gupta, M. Bansod, S. K. Gupta, and P. Whig, “AI, blockchain, and Quantum Finance: the transformative power of emerging technologies in the financial industry,” in Information systems engineering and management, 2025, pp. 1–20. doi: 10.1007/978-3-031-92916-8_1.

DOI: https://doi.org/10.64971/j.cph.ijsdip.v13.i4.16.2025