Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
129 tokens/sec
GPT-4o
28 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Taiyi: A high-performance CKKS accelerator for Practical Fully Homomorphic Encryption (2403.10188v1)

Published 15 Mar 2024 in cs.CR and cs.AR

Abstract: Fully Homomorphic Encryption (FHE), a novel cryptographic theory enabling computation directly on ciphertext data, offers significant security benefits but is hampered by substantial performance overhead. In recent years, a series of accelerator designs have significantly enhanced the performance of FHE applications, bringing them closer to real-world applicability. However, these accelerators face challenges related to large on-chip memory and area. Additionally, FHE algorithms undergo rapid development, rendering the previous accelerator designs less perfectly adapted to the evolving landscape of optimized FHE applications. In this paper, we conducted a detailed analysis of existing applications with the new FHE method, making two key observations: 1) the bottleneck of FHE applications shifts from NTT to the inner-product operation, and 2) the optimal {\alpha} of KeySwitch changes with the decrease in multiplicative level. Based on these observations, we designed an accelerator named Taiyi, which includes specific hardware for the inner-product operation and optimizes the NTT and BConv operations through algorithmic derivation. A comparative evaluation of Taiyi against previous state-of-the-art designs reveals an average performance improvement of 1.5x and reduces the area overhead by 15.7%.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. R. Agrawal, J. H. Ahn, F. Bergamaschi, R. Cammarota, J. H. Cheon, F. DM de Souza, H. Gong, M. Kang, D. Kim, J. Kim et al., “High-precision rns-ckks on fixed but smaller word-size architectures: theory and application,” in Proceedings of the 11th Workshop on Encrypted Computing & Applied Homomorphic Cryptography, 2023, pp. 23–34.
  2. R. Agrawal, L. de Castro, C. Juvekar, A. Chandrakasan, V. Vaikuntanathan, and A. Joshi, “Mad: Memory-aware design techniques for accelerating fully homomorphic encryption,” in The 56th IEEE/ACM International Symposium on Microarchitecture (MICRO).   IEEE, 2023.
  3. R. Agrawal, L. de Castro, G. Yang, C. Juvekar, R. Yazicigil, A. Chandrakasan, V. Vaikuntanathan, and A. Joshi, “Fab: An fpga-based accelerator for bootstrappable fully homomorphic encryption,” in 2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA).   IEEE, 2023, pp. 882–895.
  4. J.-C. Bajard, J. Eynard, M. A. Hasan, and V. Zucca, “A full rns variant of fv like somewhat homomorphic encryption schemes,” in Selected Areas in Cryptography–SAC 2016: 23rd International Conference, St. John’s, NL, Canada, August 10-12, 2016, Revised Selected Papers.   Springer, 2017, pp. 423–442.
  5. F. Boemer, A. Costache, R. Cammarota, and C. Wierzynski, “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, 2019, pp. 45–56.
  6. Z. Brakerski, C. Gentry, and V. Vaikuntanathan, “(leveled) fully homomorphic encryption without bootstrapping,” ACM Transactions on Computation Theory (TOCT), vol. 6, no. 3, pp. 1–36, 2014.
  7. Z. Brakerski and V. Vaikuntanathan, “Efficient fully homomorphic encryption from (standard) lwe,” SIAM Journal on computing, vol. 43, no. 2, pp. 831–871, 2014.
  8. H. Chen, I. Chillotti, and Y. Song, “Improved bootstrapping for approximate homomorphic encryption,” in Annual International Conference on the Theory and Applications of Cryptographic Techniques.   Springer, 2019, pp. 34–54.
  9. H. Chen, W. Dai, M. Kim, and Y. Song, “Efficient multi-key homomorphic encryption with packed ciphertexts with application to oblivious neural network inference,” in Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security, 2019, pp. 395–412.
  10. J. H. Cheon, K. Han, A. Kim, M. Kim, and Y. Song, “A full rns variant of approximate homomorphic encryption,” in Selected Areas in Cryptography–SAC 2018: 25th International Conference, Calgary, AB, Canada, August 15–17, 2018, Revised Selected Papers 25.   Springer, 2019, pp. 347–368.
  11. I. Chillotti, N. Gama, M. Georgieva, and M. Izabachène, “Tfhe: fast fully homomorphic encryption over the torus,” Journal of Cryptology, vol. 33, no. 1, pp. 34–91, 2020.
  12. L. de Castro, R. Agrawal, R. Yazicigil, A. Chandrakasan, V. Vaikuntanathan, C. Juvekar, and A. Joshi, “Does fully homomorphic encryption need compute acceleration?” arXiv preprint arXiv:2112.06396, 2021.
  13. J. Fan and F. Vercauteren, “Somewhat practical fully homomorphic encryption,” Cryptology ePrint Archive, 2012.
  14. S. Fan, Z. Wang, W. Xu, R. Hou, D. Meng, and M. Zhang, “Tensorfhe: Achieving practical computation on encrypted data using gpgpu,” in 2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA).   IEEE, 2023, pp. 922–934.
  15. S. Gener, P. Newton, D. Tan, S. Richelson, G. Lemieux, and P. Brisk, “An fpga-based programmable vector engine for fast fully homomorphic encryption over the torus,” in SPSL: Secure and Private Systems for Machine Learning (ISCA Workshop), 2021.
  16. Y. Ha, “Sparselwe-estimator,” https://github.com/Yongyongha/SparseLWE-estimator, 2021.
  17. K. Han, S. Hong, J. H. Cheon, and D. Park, “Logistic regression on homomorphic encrypted data at scale.” in AAAI Conference on Artificial Intelligence (AAAI), 2019, pp. 9466–9471.
  18. K. Han and D. Ki, “Better bootstrapping for approximate homomorphic encryption,” in Topics in Cryptology–CT-RSA 2020: The Cryptographers’ Track at the RSA Conference 2020, San Francisco, CA, USA, February 24–28, 2020, Proceedings.   Springer, 2020, pp. 364–390.
  19. I. Hwang, J. Seo, and Y. Song, “Optimizing he operations via level-aware key-switching framework,” Cryptology ePrint Archive, 2023.
  20. L. Jiang, Q. Lou, and N. Joshi, “Matcha: A fast and energy-efficient accelerator for fully homomorphic encryption over the torus,” in Proceedings of the 59th ACM/IEEE Design Automation Conference, 2022, pp. 235–240.
  21. W. Jung, S. Kim, J. H. Ahn, J. H. Cheon, and Y. Lee, “Over 100x faster bootstrapping in fully homomorphic encryption through memory-centric optimization with gpus,” IACR Transactions on Cryptographic Hardware and Embedded Systems, pp. 114–148, 2021.
  22. J. Kim, S. Kim, J. Choi, J. Park, D. Kim, and J. H. Ahn, “Sharp: A short-word hierarchical accelerator for robust and practical fully homomorphic encryption,” in Proceedings of the 50th Annual International Symposium on Computer Architecture, 2023, pp. 1–15.
  23. J. Kim, G. Lee, S. Kim, G. Sohn, J. Kim, M. Rhu, and J. H. Ahn, “Ark: Fully homomorphic encryption accelerator with runtime data generation and inter-operation key reuse,” arXiv preprint arXiv:2205.00922, 2022.
  24. M. Kim, D. Lee, J. Seo, and Y. Song, “Accelerating HE operations from key decomposition technique.”   CRYPTO 2023.
  25. S. Kim, J. Kim, M. J. Kim, W. Jung, J. Kim, M. Rhu, and J. H. Ahn, “Bts: An accelerator for bootstrappable fully homomorphic encryption,” in Proceedings of the 49th Annual International Symposium on Computer Architecture, 2022, pp. 711–725.
  26. E. Lee, J.-W. Lee, J. Lee, Y.-S. Kim, Y. Kim, J.-S. No, and W. Choi, “Low-complexity deep convolutional neural networks on fully homomorphic encryption using multiplexed parallel convolutions.” in International Conference on Machine Learning (ICML), 2022, pp. 12 403–12 422.
  27. J.-W. Lee, H. Kang, Y. Lee, W. Choi, J. Eom, M. Deryabin, E. Lee, J. Lee, D. Yoo, Y.-S. Kim et al., “Privacy-preserving machine learning with fully homomorphic encryption for deep neural network,” IEEE Access, vol. 10, pp. 30 039–30 054, 2022.
  28. M. Liu, “1.1 unleashing the future of innovation,” in 2021 IEEE International Solid-State Circuits Conference (ISSCC), vol. 64.   IEEE, 2021, pp. 9–16.
  29. Q. Lou, B. Feng, G. Charles Fox, and L. Jiang, “Glyph: Fast and accurately training deep neural networks on encrypted data,” Advances in neural information processing systems, vol. 33, pp. 9193–9202, 2020.
  30. Q. Lou and L. Jiang, “Hemet: A homomorphic-encryption-friendly privacy-preserving mobile neural network architecture,” in International conference on machine learning.   PMLR, 2021, pp. 7102–7110.
  31. C. Mouchet, J.-P. Bossuat, J. Troncoso-Pastoriza, and J. Hubaux, “Lattigo: A multiparty homomorphic encryption library in go,” in WAHC 2020–8th Workshop on Encrypted Computing & Applied Homomorphic Cryptography, 2020.
  32. K. Nam, H. Oh, H. Moon, and Y. Paek, “Accelerating n-bit operations over tfhe on commodity cpu-fpga,” in Proceedings of the 41st IEEE/ACM International Conference on Computer-Aided Design, ser. ICCAD ’22.   New York, NY, USA: Association for Computing Machinery, 2022. [Online]. Available: https://doi.org/10.1145/3508352.3549413
  33. A. Putra, Y. Chen, J. Kim, J.-Y. Kim et al., “Strix: An end-to-end streaming architecture with two-level ciphertext batching for fully homomorphic encryption with programmable bootstrapping,” arXiv e-prints, pp. arXiv–2305, 2023.
  34. M. S. Riazi, K. Laine, B. Pelton, and W. Dai, “Heax: An architecture for computing on encrypted data,” in Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems, 2020, pp. 1295–1309.
  35. N. Samardzic, A. Feldmann, A. Krastev, S. Devadas, R. Dreslinski, C. Peikert, and D. Sanchez, “F1: A fast and programmable accelerator for fully homomorphic encryption,” in MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture, 2021, pp. 238–252.
  36. N. Samardzic, A. Feldmann, A. Krastev, N. Manohar, N. Genise, S. Devadas, K. Eldefrawy, C. Peikert, and D. Sanchez, “Craterlake: a hardware accelerator for efficient unbounded computation on encrypted data.” in ISCA, 2022, pp. 173–187.
  37. K. Shivdikar, Y. Bao, R. Agrawal, M. Shen, G. Jonatan, E. Mora, A. Ingare, N. Livesay, J. L. Abellán, J. Kim et al., “Gme: Gpu-based microarchitectural extensions to accelerate homomorphic encryption,” arXiv preprint arXiv:2309.11001, 2023.
  38. M. Van Beirendonck, J.-P. D’Anvers, and I. Verbauwhede, “Fpt: a fixed-point accelerator for torus fully homomorphic encryption,” arXiv preprint arXiv:2211.13696, 2022.
  39. Z. Wang, P. Li, R. Hou, Z. Li, J. Cao, X. Wang, and D. Meng, “He-booster: An efficient polynomial arithmetic acceleration on gpus for fully homomorphic encryption,” IEEE Transactions on Parallel and Distributed Systems, vol. 34, no. 4, pp. 1067–1081, 2023.
  40. Y. Yang, H. Zhang, S. Fan, H. Lu, M. Zhang, and X. Li, “Poseidon: Practical homomorphic encryption accelerator,” in 2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA).   IEEE, 2023, pp. 870–881.
  41. T. Ye, R. Kannan, and V. K. Prasanna, “Fpga acceleration of fully homomorphic encryption over the torus,” in 2022 IEEE High Performance Extreme Computing Conference (HPEC).   IEEE, 2022, pp. 1–7.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now