Privacy-Preserving AI Model for IoT Networks Utilizing Differential Privacy and Secure Aggregation in Decentralized Learning Environments
Keywords:
Internet of things, K-Means clustering, Random Forest, decentralized Model, Privacy Preserving AIAbstract
The level of privacy protection needed for IoT depends on various factors and considerations. Factors such as the sensitivity of the data at stake, compliance with stringent data protection regulations, alignment with user privacy expectations, and the potential for misuse underscore the need for a nuanced approach. Additionally, the security integrity of the entire IoT ecosystem, encompassing device security, network fortification, and data storage, significantly influences the imperative for robust privacy safeguards. The work introduces a pioneering decentralized Privacy-Preserving AI system tailored for the Internet of Things (IoT), emphasizing user privacy while harnessing the collaborative power of decentralized learning. The system integrates two key algorithms, K-Means clustering and Random Forest (RF), each fortified with robust privacy-preserving mechanisms. The K-Means algorithm strategically applies Differential Privacy, introducing controlled noise during clustering to protect sensitive individual data points. Concurrently, the Random Forest algorithm employs ensemble learning, allowing each IoT device to contribute to local decision tree creation with the addition of Laplace noise for safeguarding sensitive data. The decentralized model ensures secure, peer-to-peer collaboration during updates, facilitating the creation of a Global AI Model that embodies collective knowledge. The workflow involves local data processing, privacy-preserving algorithms, secure collaborative updates, and model distribution. The proposed approach strikes a delicate balance between utility and data protection, offering a powerful and privacy-respecting solution for AI models in decentralized IoT environments. The system's architecture, algorithms, and workflow, emphasizing its significance in ensuring robust privacy while advancing AI capabilities in IoT applications.
Downloads
References
Zaman, U., Imran, Mehmood, F., Iqbal, N., Kim, J., & Ibrahim, M. (2022). Towards Secure and Intelligent Internet of Health Things: A Survey of Enabling Technologies and Applications. Electronics, 11(12), 1893.
Srivastava, A., Gupta, S., Quamara, M., Chaudhary, P., & Aski, V. J. (2020). Future IoT‐enabled threats and vulnerabilities: State of the art, challenges, and future prospects. International Journal of Communication Systems, 33(12), e4443.
Deebak, B. D., Memon, F. H., Cheng, X., Dev, K., Hu, J., Khowaja, S. A., ... & Choi, K. H. (2022). Seamless privacy-preservation and authentication framework for IoT-enabled smart eHealth systems. Sustainable Cities and Society, 80, 103661.
Rivadeneira, J. E., Silva, J. S., Colomo-Palacios, R., Rodrigues, A., & Boavida, F. (2023). User-centric privacy preserving models for a new era of the Internet of Things. Journal of Network and Computer Applications, 103695.
Tsaloli, G., Liang, B., Brunetta, C., Banegas, G., & Mitrokotsa, A. (2021, November). DEVA: Decentralized, verifiable secure aggregation for privacy-preserving learning. In International Conference on Information Security (pp. 296-319). Cham: Springer International Publishing.
Shafeeq, S., Alam, M., & Khan, A. (2019). Privacy aware decentralized access control system. Future Generation Computer Systems, 101, 420-433.
Jiang, B., Li, J., Yue, G., & Song, H. (2021). Differential privacy for industrial internet of things: Opportunities, applications, and challenges. IEEE Internet of Things Journal, 8(13), 10430-10451.
Kasyap, H., & Tripathy, S. (2021). Privacy-preserving decentralized learning framework for healthcare system. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 17(2s), 1-24.
Abiodun, M. K., Awotunde, J. B., Ogundokun, R. O., Adeniyi, E. A., & Arowolo, M. O. (2021). Security and information assurance for IoT-based big data. In Artificial Intelligence for Cyber Security: Methods, Issues and Possible Horizons or Opportunities (pp. 189-211). Cham: Springer International Publishing.
Satyanarayana, P., Diwakar, G., Subbayamma, B. V., Phani Sai Kumar, N. V., Arun, M., & Gopalakrishnan, S. (2023). Comparative analysis of new meta-heuristic-variants for privacy preservation in wireless mobile adhoc networks for IoT applications. Computer Communications, 198, 262–281. https://doi.org/10.1016/ j.comcom. 2022.12.006.
Yamac, M., Ahishali, M., Passalis, N., Raitoharju, J., Sankur, B., & Gabbouj, M. (2020). Multi-level reversible data anonymization via compressive sensing and data hiding. IEEE Transactions on Information Forensics and Security, 16, 1014-1028.
Grammatikis, P. I. R., Sarigiannidis, P. G., & Moscholios, I. D. (2019). Securing the Internet of Things: Challenges, threats and solutions. Internet of Things, 5, 41-70.
Rai, R. K. (2022). Data Mining Of Perturbation Data Approach Using Different Noise For Privacy Preserving Techniques. Neuro Quantology, 20(9), 4039.
Keshk, M., Moustafa, N., Sitnikova, E., Turnbull, B., & Vatsalan, D. (2020, December). Privacy-preserving techniques for protecting large-scale data of cyber-physical systems. In 2020 16th international conference on mobility, sensing and networking (MSN) (pp. 711-717). IEEE.
Arachchige, P. C. M. (2020). Scalable data perturbation for privacy preserving large scale data analytics and machine learning (Doctoral dissertation, RMIT University).
Perumal, G., Subburayalu, G., Abbas, Q., Naqi, S. M., & Qureshi, I. (2023). VBQ-Net: A Novel Vectorization-Based Boost Quantized Network Model for Maximizing the Security Level of IoT System to Prevent Intrusions. Systems, 11(8), 436. MDPI AG.
Rachapudi V., Venkata Suryanarayana S., Subha Mastan Rao T. "Auto-encoder based K-means clustering algorithm". International Journal of Innovative Technology and Exploring Engineering. 2019. 8(5), pp. 1223-1226
Kallam, Suresh, A. Veerender, K. Shilpa, K. Ranjith Reddy, K. Reddy Madhavi, and Jonnadula Narasimharao. "The Adaptive Strategies Improving Design in Internet of Things." In Proceedings of Third International Conference on Advances in Computer Engineering and Communication Systems: ICACECS 2022, pp. 691-699. Singapore: Springer Nature Singapore, 2023.
Kumar Apat, S., Mishra, J., Srujan Raju, K., Padhy, N. (2023). IoT-Assisted Crop Monitoring Using Machine Learning Algorithms for Smart Farming. In: Kumar, R., Pattnaik, P.K., R. S. Tavares, J.M. (eds) Next Generation of Internet of Things. Lecture Notes in Networks and Systems, vol 445. Springer, Singapore. https://doi.org/10.1007/978-981-19-1412-6_1
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
