Lightweight Cryptographic Inference for Adaptive Deep Learning at the Edge

Authors

  • Pranit Gera School of Information Technology, University of Cincinnati, Cincinnati, OH, USA. Author

Keywords:

edge computing, private inference, adaptive deep learning, lightweight cryptography, secure multiparty computation, homomorphic encryption, socio-technical systems, governance, sustainability

Abstract

Edge computing has shifted artificial intelligence away from centralized data centers toward devices, gateways, and near-user infrastructure, creating new possibilities for responsive deep learning while intensifying concerns about privacy, trust, and resource constraints. This paper examines lightweight cryptographic inference for adaptive deep learning at the edge, focusing on the structural tensions among model adaptivity, cryptographic protection, latency, energy use, governance, and long-term sustainability. Adaptive deep learning allows models to alter computation according to input difficulty, context, device state, or risk, but cryptographic inference imposes distinct cost profiles on linear layers, nonlinear activations, data movement, and model selection. The analysis therefore treats private inference not as a single primitive but as a socio-technical architecture that couples cryptographic protocols, model design, hardware acceleration, orchestration, and policy. The paper reviews foundations in homomorphic encryption, secure multiparty computation, and hybrid protocols, then considers how compression, pruning, distillation, and conditional computation reshape cryptographic workloads. It argues that lightweight cryptographic inference must be assessed through end-to-end system metrics, including tail latency, thermal behavior, battery impact, auditability, and equitable service quality. Governance questions are equally important, because adaptive private inference can obscure accountability when model paths, cryptographic providers, or edge operators change dynamically. Through cross-domain comparisons and forward-looking analysis, the paper proposes that adaptive private inference at the edge should be designed as a governed infrastructure capability rather than an isolated optimization problem. The conclusion emphasizes robustness, fairness, deployment realism, and sustainability as first-order design criteria.

References

1. Satyanarayanan, M. (2017). The emergence of edge computing. Computer, 50(1), 30-39. https://doi.org/10.1109/MC.2017.9

2. Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016). Edge computing: Vision and challenges. IEEE Internet of Things Journal, 3(5), 637-646. https://doi.org/10.1109/JIOT.2016.2579198

3. Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J. (2019). Edge intelligence: Paving the last mile of artificial intelligence with edge computing. Proceedings of the IEEE, 107(8), 1738-1762. https://doi.org/10.1109/JPROC.2019.2918951

4. Dhar, S., Guo, J., Liu, J., Tripathi, S., Kurup, U., & Shah, M. (2021). A survey of on-device machine learning: An algorithms and learning theory perspective. ACM Transactions on Internet of Things, 2(3), 1-28. https://doi.org/10.1145/3450494

5. Gentry, C. (2009). Fully homomorphic encryption using ideal lattices. In Proceedings of the 41st Annual ACM Symposium on Theory of Computing (pp. 169-178). https://doi.org/10.1145/1536414.1536440

6. Zhou, T., Zhao, J., Luo, Y., Xie, X., Wen, W., Ding, C., & Xu, X. (2024, October). Adapi: Facilitating dnn model adaptivity for efficient private inference in edge computing. In Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design (pp. 1-9).

7. Juvekar, C., Vaikuntanathan, V., & Chandrakasan, A. (2018). GAZELLE: A low latency framework for secure neural network inference. In Proceedings of the 27th USENIX Security Symposium (pp. 1651-1669). USENIX Association.

8. Liu, J., Juuti, M., Lu, Y., & Asokan, N. (2017). Oblivious neural network predictions via MiniONN transformations. In Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security (pp. 619-631). https://doi.org/10.1145/3133956.3134056

9. Mohassel, P., & Zhang, Y. (2017). SecureML: A system for scalable privacy-preserving machine learning. In 2017 IEEE Symposium on Security and Privacy (pp. 19-38). https://doi.org/10.1109/SP.2017.12

10. Riazi, M. S., Weinert, C., Tkachenko, O., Songhori, E. M., Schneider, T., & Koushanfar, F. (2018). Chameleon: A hybrid secure computation framework for machine learning applications. In Proceedings of the 2018 on Asia Conference on Computer and Communications Security (pp. 707-721). https://doi.org/10.1145/3196494.3196522

11. Mishra, P., Lehmkuhl, R., Srinivasan, A., Zheng, W., & Popa, R. A. (2020). Delphi: A cryptographic inference service for neural networks. In Proceedings of the 29th USENIX Security Symposium (pp. 2505-2522). USENIX Association.

12. Rathee, D., Rathee, M., Kumar, N., Chandran, N., Gupta, D., Rastogi, A., & Sharma, R. (2020). CrypTFlow2: Practical 2-party secure inference. In Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security (pp. 325-342). https://doi.org/10.1145/3372297.3417274

13. Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv. https://arxiv.org/abs/1704.04861

14. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 4510-4520). https://doi.org/10.1109/CVPR.2018.00474

15. Han, S., Pool, J., Tran, J., & Dally, W. (2015). Learning both weights and connections for efficient neural network. In Advances in Neural Information Processing Systems (Vol. 28, pp. 1135-1143). Curran Associates.

16. Frankle, J., & Carbin, M. (2019). The lottery ticket hypothesis: Finding sparse, trainable neural networks. In International Conference on Learning Representations. https://openreview.net/forum?id=rJl-b3RcF7

17. Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv. https://arxiv.org/abs/1503.02531

18. Goldwasser, S., Micali, S., & Rackoff, C. (1989). The knowledge complexity of interactive proof systems. SIAM Journal on Computing, 18(1), 186-208. https://doi.org/10.1137/0218012

19. Boneh, D., & Franklin, M. (2001). Identity-based encryption from the Weil pairing. In Advances in Cryptology - CRYPTO 2001 (pp. 213-229). Springer. https://doi.org/10.1007/3-540-44647-8_13

20. Acar, A., Aksu, H., Uluagac, A. S., & Conti, M. (2018). A survey on homomorphic encryption schemes: Theory and implementation. ACM Computing Surveys, 51(4), 1-35. https://doi.org/10.1145/3214303

Downloads

Published

2026-10-23