Abstract
Fully Homomorphic Encryption (FHE) enables computation on encrypted data and can be used to provide privacy-preserving computation for machine learning models. However, FHE is computationally expensive and requires significant memory. Single instruction multiple data (SIMD) can offset this cost. Batch-packing, an SIMD technique that packs data along the batch dimension, requires significant memory. In convolutional neural networks, we can exploit their regular and repeating structure to reduce the memory cost by caching recurring values. In this paper, we investigate strategies for dynamically loading data from persistent storage and how to cache it effectively. We propose a method that reorders operations inside the convectional layer to increase caching effectiveness and reduce memory requirements. We achieve up to 50x reduction in memory requirements with only a 13% increase in runtime compared to keeping the data in memory during the entire computation. Our method is up to 38% faster at no significant memory difference compared to not using caching. We also show that our approach is up to 4.5x faster than the operating system’s swapping technique. These improvements allow us to run the models on less powerful and cheaper hardware.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abadi, M., et al.: Deep learning with differential privacy. In: Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, pp. 308–318 (2016)
Aharoni, E., et al.: HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data. Proceedings on Privacy Enhancing Technologies 2023(1), 325–342 (Jan 2023). https://doi.org/10.56553/popets-2023-0020, http://arxiv.org/abs/2011.01805, arXiv:2011.01805 [cs]
Akavia, A., Oren, N., Sapir, B., Vald, M.: Compact storage for homomorphic encryption. Cryptology ePrint Archive (2022)
Al Badawi, A., et al.: Towards the AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data with GPUs. IEEE Trans. Emerg. Topics Comput. (2020). https://doi.org/10.1109/TETC.2020.3014636, conference Name: IEEE Transactions on Emerging Topics in Computing
Al Badawi, A., et al.: OpenFHE: open-source fully homomorphic encryption library. in: proceedings of the 10th workshop on encrypted computing & applied homomorphic cryptography, pp. 53–63. WAHC’22, Association for Computing Machinery, New York, NY, USA (2022). https://doi.org/10.1145/3560827.3563379 event-place: Los Angeles, CA, USA
Amazon.com, I.: Amazon alexa voice ai, alexa developer offical site. https://developer.amazon.com/en-US/alexa Accessed 17 Oct 2023
Boemer, F., Costache, A., Cammarota, R., Wierzynski, C.: ngraph-he2: A high-throughput framework for neural network inference on encrypted data. In: Proceedings of the 7th ACM Workshop on Encrypted Computing & Applied Homomorphic Cryptography, pp. 45–56 (2019)
Boemer, F., Lao, Y., Cammarota, R., Wierzynski, C.: ngraph-he: a graph compiler for deep learning on homomorphically encrypted data. In: Proceedings of the 16th ACM International Conference on Computing Frontiers, pp. 3–13 (2019)
Brutzkus, A., Gilad-Bachrach, R., Elisha, O.: Low latency privacy preserving inference. In: International Conference on Machine Learning, pp. 812–821. PMLR (2019)
Cai, Y., Zhang, Q., Ning, R., Xin, C., Wu, H.: Hunter: he-friendly structured pruning for efficient privacy-preserving deep learning. In: Proceedings of the 2022 ACM on Asia Conference on Computer and Communications Security, pp. 931–945 (2022)
Chabanne, H., de Wargny, A., Milgram, J., Morel, C., Prouff, E.: Privacy-preserving classification on deep neural network. IACR Cryptol. ePrint Arch. 2017, 35 (2017)
Chaudhari, H., Rachuri, R., Suresh, A.: Trident: efficient 4pc framework for privacy preserving machine learning. In: Proceedings 2020 Network and Distributed System Security Symposium. NDSS 2020, Internet Society (2020). https://doi.org/10.14722/ndss.2020.23005, http://dx.doi.org/10.14722/ndss.2020.23005
Cheon, J.H., Han, K., Kim, A., Kim, M., Song, Y.: A full RNS variant of approximate homomorphic encryption. In: Cid, C., Jacobson, M.J. (eds.) Selected Areas in Cryptography – SAC 2018: 25th International Conference, Calgary, AB, Canada, August 15–17, 2018, Revised Selected Papers, pp. 347–368. Springer International Publishing, Cham (2019). https://doi.org/10.1007/978-3-030-10970-7_16
Choi, W.S., Reagen, B., Wei, G.Y., Brooks, D.: Impala: Low-Latency, Communication-Efficient Private Deep Learning Inference. arXiv preprint arXiv:2205.06437 (2022)
Dathathri, R., et al.: CHET: an optimizing compiler for fully-homomorphic neural-network inferencing. In: Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation, pp. 142–156. PLDI 2019, Association for Computing Machinery, New York, NY, USA (Jun 2019). https://doi.org/10.1145/3314221.3314628, https://doi.org/10.1145/3314221.3314628
Dilsizian, S.E., Siegel, E.L.: Artificial intelligence in medicine and cardiac imaging: harnessing big data and advanced computing to provide personalized medical diagnosis and treatment. Curr. Cardiol. Rep. 16, 1–8 (2014)
Dowlin, N., Gilad-Bachrach, R., Laine, K., Lauter, K., Naehrig, M., Wernsing, J.: Cryptonets: applying neural networks to encrypted data with high throughput and accuracy. In: International Conference on Machine Learning, pp. 201–210 (2016)
Dwork, C., Roth, A.: The algorithmic foundations of differential privacy. Found. Trends Theor. Comput. Sci. 9(3–4), 211–407 (2014)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016). http://www.deeplearningbook.org
Google, I.: Bard - chat based ai tool from google, powered by palm2. https://bard.google.com/ Accessed 17 Oct 2023
Google, I.: Google assitant, your own personal google. https://assistant.google.com/Accessed 17 Oct 2023
Grammarly, I.: Grammarly: free writing ai assistance. https://www.grammarly.com/Accessed 17 Oct 2023
Hao, M., Li, H., Chen, H., Xing, P., Xu, G., Zhang, T.: Iron: Private Inference on Transformers. In: Advances in Neural Information Processing Systems (2022)
Hesamifard, E., Takabi, H., Ghasemi, M.: Cryptodl: Deep neural networks over encrypted data. arXiv preprint arXiv:1711.05189 (2017)
Hesamifard, E., Takabi, H., Ghasemi, M.: Deep Neural networks classification over encrypted data. In: Proceedings of the Ninth ACM Conference on Data and Application Security and Privacy, pp. 97–108. ACM, Richardson Texas USA (Mar 2019). https://doi.org/10.1145/3292006.3300044
Huang, Z., Lu, W.j., Hong, C., Ding, J.: Cheetah: Lean and Fast Secure $$two-party$$ Deep Neural Network Inference. In: 31st USENIX Security Symposium (USENIX Security 22), pp. 809–826 (2022)
Inc., A.: Siri - apple. https://www.apple.com/siri/ Accessed 17 Oct 2023
Jiang, X., Kim, M., Lauter, K., Song, Y.: Secure outsourced matrix computation and application to neural networks. In: Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security. pp. 1209–1222. ACM, Toronto Canada (Oct 2018). https://doi.org/10.1145/3243734.3243837
Juvekar, C., Vaikuntanathan, V., Chandrakasan, A.: GAZELLE: a low latency framework for secure neural network inference. In: 27th USENIX Security Symposium (USENIX Security 18), pp. 1651–1669 (2018)
Kashyap, A., Plis, S., Ritter, P., Keilholz, S.: A deep learning approach to estimating initial conditions of brain network models in reference to measured fmri data. Front. Neurosci. 17 (2023)
Kim, D., Park, J., Kim, J., Kim, S., Ahn, J.H.: HyPHEN: A Hybrid Packing Method and Optimizations for Homomorphic Encryption-Based Neural Networks. arXiv preprint arXiv:2302.02407 (2023)
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images,: publisher: Toronto. ON, Canada (2009)
Lee, E., et al.: Low-complexity deep convolutional neural networks on fully homomorphic encryption using multiplexed parallel convolutions. In: International Conference on Machine Learning, pp. 12403–12422. PMLR (2022)
Lee, J.W., et al.: Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network. IEEE Access 10, 30039–30054 (2022). https://doi.org/10.1109/ACCESS.2022.3159694, conference Name: IEEE Access
Li, B., Micciancio, D.: On the security of homomorphic encryption on approximate numbers. In: Canteaut, A., Standaert, F.-X. (eds.) Advances in Cryptology – EUROCRYPT 2021: 40th Annual International Conference on the Theory and Applications of Cryptographic Techniques, Zagreb, Croatia, October 17–21, 2021, Proceedings, Part I, pp. 648–677. Springer International Publishing, Cham (2021). https://doi.org/10.1007/978-3-030-77870-5_23
Li, S., et al.: FALCON: a fourier transform based approach for fast and secure convolutional neural network predictions. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8702–8711. IEEE, Seattle, WA, USA (Jun 2020). https://doi.org/10.1109/CVPR42600.2020.00873, https://ieeexplore.ieee.org/document/9156980/
Liu, J., Juuti, M., Lu, Y., Asokan, N.: Oblivious neural network predictions via minionn transformations. In: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, pp. 619–631 (2017)
Mohassel, P., Zhang, Y.: SecureML: a system for scalable privacy-preserving machine learning. In: 2017 IEEE Symposium on Security and Privacy (SP), pp. 19–38 (May 2017). https://doi.org/10.1109/SP.2017.12, iSSN: 2375-1207
OpenAI: Chatgpt. https://openai.com/chatgpt Accessed 17 Oct 2023
Papernot, N., Song, S., Mironov, I., Raghunathan, A., Talwar, K., Erlingsson, U.: Scalable private learning with pate. arXiv preprint arXiv:1802.08908 (2018)
Podschwadt, R., Takabi, D.: Classification of encrypted word embeddings using recurrent neural networks. In: PrivateNLP@ WSDM, pp. 27–31 (2020)
Podschwadt, R., Takabi, D.: Non-interactive privacy preserving recurrent neural network prediction with homomorphic encryption. In: 2021 IEEE 14th International Conference on Cloud Computing (CLOUD), pp. 65–70. IEEE (2021)
Shivdikar, K., et al.: Accelerating polynomial multiplication for homomorphic encryption on gpus. In: 2022 IEEE International Symposium on Secure and Private Execution Environment Design (SEED), pp. 61–72. IEEE (2022)
Smart, N.. P.., Vercauteren, F..: Fully homomorphic SIMD operations. Designs, Codes and Cryptography 71(1), 57–81 (2014). https://doi.org/10.1007/s10623-012-9720-4
Tramèr, F., Zhang, F., Juels, A., Reiter, M.K., Ristenpart, T.: Stealing Machine Learning Models via Prediction \$\$apis\$\$. In: 25th USENIX security symposium (USENIX Security 16), pp. 601–618 (2016)
Zheng, M., Lou, Q., Jiang, L.: Primer: fast private transformer inference on encrypted data (Mar 2023). arXiv:2303.13679 [cs]
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Podschwadt, R., Ghazvinian, P., GhasemiGol, M., Takabi, D. (2024). Memory Efficient Privacy-Preserving Machine Learning Based on Homomorphic Encryption. In: Pöpper, C., Batina, L. (eds) Applied Cryptography and Network Security. ACNS 2024. Lecture Notes in Computer Science, vol 14584. Springer, Cham. https://doi.org/10.1007/978-3-031-54773-7_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-54773-7_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-54772-0
Online ISBN: 978-3-031-54773-7
eBook Packages: Computer ScienceComputer Science (R0)