Adaptive multi-resource covert communication framework for embedded and distributed learning systems
*Naveen KulkarniCorresponding authornaveenk-cse@dsu.edu.inDepartment of Computer Science and Engineering (Cyber Security)Dayananda Sagar UniversityBangalore, Karnataka, 562112, IndiaView full profile → , Mohamed Aneesanees@vvce.ac.inDepartment of Electronics and Communication EngineeringVidyavardhaka College of EngineeringMysuru, Karnataka, 570017, IndiaView full profile → , M. Jyothirmaimjyothirmaiece@recw.ac.inDepartment of Electronics and Communication EngineeringRavindra College of Engineering for WomenKurnool, Andhra Pradesh, 518452, IndiaView full profile → , A. PratimaPratima.may10@gmail.comDepartment of AI & RoboticsSchool of EngineeringDayananda Sagar UniversityBangalore, Karnataka, 562112, IndiaView full profile → , Kondru Ayyappa Swamyayyappa.kondru@gmail.comDepartment of Electronics and Communication EngineeringAditya UniversitySurampalem, Andhra Pradesh, 533437, IndiaView full profile → , T. S. Deepthi Murthydeepthiresearch1983@gmail.comSchool of Electronics and Communication EngineeringREVA UniversityBangalore, Karnataka, 560064, IndiaView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Mar 2026
- Published Online:
- 31 Aug 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JIOS-2360
- Pages:
- 2867–2876
Abstract
Modern computing environments, such as embedded systems and distributed learning environments, exhibit stochastic and dynamic behavior due to effects such as dynamic voltage and frequency scaling (DVFS), heterogeneous multicore architectures, thermal management, workload interference, and privacy-preserving operations such as differential privacy. All of these effects render traditional constant-parameter covert communication unstable at conventional modulation rates, resulting in impractically high bit error rates (BER) and detectability. This paper describes a unified Adaptive Multi-Resource Covert Communication Framework that uses real-time system-state monitoring and closed-loop control to tune bit duration, modulation amplitude, spreading factor, and error-correction rate. An information-theoretic model of mutual information, state-dependent SNR, channel capacity, and KL-divergence-based stealth metrics captures the statistical properties of resource-heterogeneous systems under stochastic workloads. The framework is evaluated on two important scenarios: embedded multicore systems under DVFS and thermal variation, and federated learning environments where gradient noise induced by differential privacy limits channel capacity. Evaluation results show that adaptive multi-resource covert channels deliver reliable transmission, high-throughput stability, and statistical stealth, surpassing both fixed-load and single-resource covert channels.
Keywords
Subject Classifications
References
[1] N. A. Jalali and H. Chen, “Federated learning security and privacy-preserving algorithm and experiments research under Internet of Things critical infrastructure,” Tsinghua Sci. Technol., vol. 29, no. 2, pp. 400–414 (Apr. 2024).
[2] J. González-Gómez, M. B. Sikal, H. Khdr, L. Bauer, and J. Henkel, “Balancing security and efficiency: System-informed mitigation of power-based covert channels,” IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst., vol. 43, no. 11, pp. 3395–3406 (Nov. 2024).
[3] N. Mishra, R. A. Mool, A. Chakraborty, and D. Mukhopadhyay, “Plug your volt: Protecting Intel processors against dynamic voltage frequency scaling based fault attacks,” in Proc. 61st ACM/IEEE Des. Autom. Conf. (DAC), San Francisco, CA, USA, pp. 1–6 (2024).
[4] K. Dhananjay, V. F. Pavlidis, A. K. Coskun, and E. Salman, “Enhanced detection of thermal covert channel attacks in multicore processors,” in Proc. 25th Int. Symp. Qual. Electron. Des. (ISQED), pp. 1–7 (2024).
[5] J. Hu, J. Du, Z. Wang, X. Pang, Y. Zhou, P. Sun, and K. Ren, “Does differential privacy really protect federated learning from gradient leakage attacks?,” IEEE Trans. Mobile Comput., vol. 23, no. 12, pp. 12635–12649 (Dec. 2024).
[6] S. Zhang, J. Huang, P. Li, and C. Liang, “Differentially private federated learning with local momentum updates and gradients filtering,” Inf. Sci., vol. 680, Art. no. 121173 (2024).
[7] Y. Cai, W. Ding, Y. Xiao, Z. Yan, X. Liu and Z. Wan, “SecFed: A Secure and Efficient Federated Learning Based on Multi-Key Homomorphic Encryption,” in IEEE Transactions on Dependable and Secure Computing, vol. 21, no. 4, pp. 3817-3833 (July-Aug. 2024), doi: 10.1109/TDSC.2023.3336977.
[8] M. Ficco, A. Guerriero, E. Milite, F. Palmieri, R. Pietrantuono, and S. Russo, “Federated learning for IoT devices: Enhancing TinyML with on-board training,” Inf. Fusion, vol. 104, Art. no. 102177 (2024).
[9] K. Peng, P. Xiao, S. Wang, and V. C. M. Leung, “SCOF: Security-Aware Computation Offloading Using Federated Reinforcement Learning in Industrial Internet of Things With Edge Computing,” in IEEE Transactions on Services Computing, vol. 17, no. 4, pp. 1780-1792 (July-Aug. 2024), doi: 10.1109/TSC.2024.3377899.
[10] S. Ismail, M. Nouman, D. W. Dawoud, and H. Reza, “Towards a lightweight security framework using blockchain and machine learning,” Blockchain: Res. Appl., vol. 5, no. 1, Art. no. 100180 (2024).
[11] Z. Li, J. Shi, J. Si, L. Lv, L. Guan, B. Hao, Z. Tie, D. Wang, C. Xing, and T. Q. S. Quek, “Intelligent covert communication: Recent advances and future research trends,” Engineering, vol. 44, no. 1, pp. 101–111 (2025), doi: 10.1016/j.eng.2024.12.007.
[12] R. Dong, B. Cui, Y. Sun, and J. Yang, “A combined side-channel and transient execution attack scheme on RISC-V processors,” Comput. Secur., vol. 150, Art. no. 104244 (2025).
[13] A. Ragab, M. Ammar, and A. Youssef, “Cache side-channel attacks and countermeasures on RISC-V processors: A survey,” IEEE Access, vol. 12, pp. 112345–112370 (2024).
[14] A. Elgabli and W. Mesbah, “A novel approach for differential privacy-preserving federated learning,” IEEE Open J. Commun. Soc., vol. 6, pp. 466–476 (2025).
[15] S. K. Das, H. Singh, and A. K. Singh, “Thermal covert channel attacks in multicore processors: Detection and mitigation techniques,” IEEE Access, vol. 12, pp. 98765–98783 (2024).
[16] D. Goyal, A. Kumar, P. Mathur, F. Sheth, and A. K. Gupta, “Robust cybersecurity through discrete and large language models for effective phishing attack detection,” J. Discrete Math. Sci. Cryptogr., vol. 28, no. 5-A, pp. 1621–1638 (2025), doi: 10.47974/JDMSC-2162.
[17] A. Noonia, D. Thakral, P. Mathur, F. Sheth, H. Shaikh, and A. K. Gupta, “A discrete mathematical model and cryptography for secure medical image analysis: Encrypted chest X-ray classification,” J. Discrete Math. Sci. Cryptogr., vol. 28, no. 5-A, pp. 1473–1486 (2025), doi: 10.47974/JDMSC-2146.
