Threat Mitigation and Privacy Strategies for Secure Artificial Intelligence and Machine Learning Workflows in Cloud Environments
Received: 23 May 2025 | Revised: 17 June 2025 and 4 July 2025 | Accepted: 23 July 2025 | Online: 6 October 2025
Corresponding author: G. Suvarna Kumar
Abstract
The adoption of Artificial Intelligence (AI) and Machine Learning (ML) in cloud computing has established new means of scalability and efficiency for data-driven applications. However, such integration also raises security and privacy risks, including adversarial attacks, and is subject to the leakage of sensitive data. To address such issues, this paper proposes a substantial threat mitigation and privacy-protection framework specifically designed for AI/ML workflows deployed on the cloud. The developed framework incorporates adversarial robustness techniques and differential privacy methods to establish a robust security model. Through comparative analysis and extensive experimentation, the framework significantly improves both robustness and privacy. Specifically, it attains 92% accuracy, 85% adversarial robustness, and 90% privacy score, outperforming the state-of-the-art algorithms. The results demonstrate the effectiveness of the proposed methodology for safeguarding AI pipelines in distributed environments, providing a practical foundation for designing secure, privacy-aware cloud-based AI/ML systems.
Keywords:
cloud AI security, adversarial attacks, access control, data poisoning, differential privacyDownloads
References
D. Patel et al., "Cloud Platforms for Developing Generative AI Solutions: A Scoping Review of Tools and Services." arXiv, Dec. 08, 2024.
A. Habbal, M. K. Ali, and M. A. Abuzaraida, "Artificial Intelligence Trust, Risk and Security Management (AI TRiSM): Frameworks, applications, challenges and future research directions," Expert Systems with Applications, vol. 240, Apr. 2024, Art. no. 122442. DOI: https://doi.org/10.1016/j.eswa.2023.122442
A. Saini and R. Sehrawat, "Enhancing Data Security through Machine Learning-based Key Generation and Encryption," Engineering, Technology & Applied Science Research, vol. 14, no. 3, pp. 14148–14154, Jun. 2024. DOI: https://doi.org/10.48084/etasr.7181
S. K. Jagatheesaperumal, M. Rahouti, K. Ahmad, A. Al-Fuqaha, and M. Guizani, "The Duo of Artificial Intelligence and Big Data for Industry 4.0: Applications, Techniques, Challenges, and Future Research Directions," IEEE Internet of Things Journal, vol. 9, no. 15, pp. 12861–12885, Aug. 2022. DOI: https://doi.org/10.1109/JIOT.2021.3139827
J. S. Kumar, A. Gupta, S. Tanwar, N. Kumar, and S. Akleylek, "Security enhancement in cellular networks employing D2D friendly jammer for V2V communication," Cluster Computing, vol. 26, no. 2, pp. 865–878, Apr. 2023. DOI: https://doi.org/10.1007/s10586-022-03551-0
M. A. M. Farzaan, M. C. Ghanem, A. El-Hajjar, and D. N. Ratnayake, "AI-Enabled System for Efficient and Effective Cyber Incident Detection and Response in Cloud Environments." arXiv, Jan. 12, 2025. DOI: https://doi.org/10.1109/TMLCN.2025.3564912
J. Robertson, J. M. Fossaceca, and K. W. Bennett, "A Cloud-Based Computing Framework for Artificial Intelligence Innovation in Support of Multidomain Operations," IEEE Transactions on Engineering Management, vol. 69, no. 6, pp. 3913–3922, Dec. 2022. DOI: https://doi.org/10.1109/TEM.2021.3088382
V. H. Das Chowdary, A. Shanmukh, T. P. Nikhil, B. S. Kumar, and F. Khan, "DevOps 2.0: Embracing AI/ML, Cloud-Native Development, and a Culture of Continuous Transformation," in 2024 4th International Conference on Pervasive Computing and Social Networking, Salem, India, 2024, pp. 673–679. DOI: https://doi.org/10.1109/ICPCSN62568.2024.00112
S. Tuli, G. Casale, and N. R. Jennings, "MCDS: AI Augmented Workflow Scheduling in Mobile Edge Cloud Computing Systems," IEEE Transactions on Parallel and Distributed Systems, vol. 33, no. 11, pp. 2794–2807, Nov. 2022.
E. Zeydan, S. S. Arslan, and M. Liyanage, "Managing Distributed Machine Learning Lifecycle for Healthcare Data in the Cloud," IEEE Access, vol. 12, pp. 115750–115774, 2024. DOI: https://doi.org/10.1109/ACCESS.2024.3443520
P. Abinaya and J. S. Kumar, "Assured and Provable Data Expuncturing in cloud using Ciphertext Policy–Attribute Based Encryption (CP-ABE)," Cybernetics and Systems, vol. 55, no. 4, pp. 786–803, May 2024. DOI: https://doi.org/10.1080/01969722.2023.2176654
J. Ejarque et al., "Enabling dynamic and intelligent workflows for HPC, data analytics, and AI convergence," Future Generation Computer Systems, vol. 134, pp. 414–429, Sep. 2022. DOI: https://doi.org/10.1016/j.future.2022.04.014
A. Giannopoulos et al., "Supporting Intelligence in Disaggregated Open Radio Access Networks: Architectural Principles, AI/ML Workflow, and Use Cases," IEEE Access, vol. 10, pp. 39580–39595, 2022. DOI: https://doi.org/10.1109/ACCESS.2022.3166160
E. e Oliveira, M. Rodrigues, J. P. Pereira, A. M. Lopes, I. I. Mestric, and S. Bjelogrlic, "Unlabeled learning algorithms and operations: overview and future trends in defense sector," Artificial Intelligence Review, vol. 57, no. 3, Feb. 2024, Art. no. 66. DOI: https://doi.org/10.1007/s10462-023-10692-0
M. Rahouti, D. Lyons, S. K. Jagatheesaperumal, and K. Xiong, "A Decentralized Cooperative Navigation Approach for Visual Homing Networks," IT Professional, vol. 25, no. 6, pp. 71–81, Nov. 2023. DOI: https://doi.org/10.1109/MITP.2023.3323865
"MNIST Dataset." Kaggle. [Online]. Available: https://www.kaggle.com/datasets/hojjatk/mnist-dataset.
W. Cukierski, "CIFAR-10 - Object Recognition in Images." Kaggle, 2013. [Online]. Available: https://kaggle.com/cifar-10.
C. Niloor, R. Agarwal, and P. Mishra, "Using MNIST Dataset for De-Pois Attack and Defence," in Fourth International Conference on Recent Trends in Communication and Intelligent Systems, Jaipur, India, 2023, pp. 213–227. DOI: https://doi.org/10.1007/978-981-99-5792-7_17
X. Cao, M. Rahouti, S. K. Jagatheesaperumal, and K. Xiong, "Psychological Information Sharing Using Ethereum Blockchain and Smart Contracts," in 2023 Fifth International Conference on Blockchain Computing and Applications, Kuwait, Kuwait, 2023, pp. 561–568. DOI: https://doi.org/10.1109/BCCA58897.2023.10338936
M. Uddin, S. Islam, and A. Al-Nemrat, "A Dynamic Access Control Model Using Authorising Workflow and Task-Role-Based Access Control," IEEE Access, vol. 7, pp. 166676–166689, 2019. DOI: https://doi.org/10.1109/ACCESS.2019.2947377
T. Zhu, D. Ye, W. Wang, W. Zhou, and P. S. Yu, "More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligence," IEEE Transactions on Knowledge and Data Engineering, vol. 34, no. 6, pp. 2824–2843, Jun. 2022. DOI: https://doi.org/10.1109/TKDE.2020.3014246
J. Pang and G. Cheung, "Graph Laplacian Regularization for Image Denoising: Analysis in the Continuous Domain," IEEE Transactions on Image Processing, vol. 26, no. 4, pp. 1770–1785, Apr. 2017. DOI: https://doi.org/10.1109/TIP.2017.2651400
T. Elgamrani, R. Elgaf, and Y. Chtouki, "Adversarial Attack Defense Techniques: A Study of Defensive Distillation and Adversarial Re-Training on CIFAR-10 and MNIST," in 2024 International Conference on Computer and Applications, Cairo, Egypt, 2024, pp. 1–4. DOI: https://doi.org/10.1109/ICCA62237.2024.10927831
J. J. Hathaliya, S. Tanwar, and P. Sharma, "Adversarial learning techniques for security and privacy preservation: A comprehensive review," Security and Privacy, vol. 5, no. 3, May 2022, Art. no. e209. DOI: https://doi.org/10.1002/spy2.209
Downloads
How to Cite
License
Copyright (c) 2025 G. Suvarna Kumar, G. Sandhya Devi, P. Mohamed Sajid, K. A. Jyostna, V. Sangeetha, Sateesh Gorikapudi, Tanweer Alam, T. Prabhakaran
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
