Abstract
Convolutional neural networks (CNNs) have emerged as one of the most successful deep learning approaches to image recognition and classification. A recent line of research, which includes zkCNN (ACM CCS ’21), vCNN (Cryptology ePrint Archive), and ZEN (Cryptology ePrint Archive), aims at protecting the privacy of CNN models by developing publicly verifiable proofs of correct classification which do not leak any information about the underlying CNN models themselves. A shared feature of these schemes is that they require the entity constructing the proof to have access to both the model and the input in the clear. In other words, a client holding a potentially sensitive input is required to reveal this input to the entity holding the CNN model, thereby sacrificing his privacy, to be able to obtain a verifiable proof of correct classification. This is in contrast to the security guarantees provided by secure classification considered in privacy-preserving machine learning, which does not require the client to reveal his input to obtain a (non-verifiable) classification.
In this paper, we propose a privacy-preserving verifiable CNN scheme that overcomes this limitation of the previous schemes by allowing the client to obtain a classification proof without having to reveal his input. The obtained proof allows the client to selectively reveal properties of the obtained classification and his input, which will be verifiable to any third-party verifier. Our scheme is based on the recent notion of collaborative zk-SNARKs by Ozdemir and Boneh (USENIX ’22). Specifically, we construct a new collaborative zk-SNARK based on Bulletproofs achieving an efficient maliciously secure proof generation protocol. Based on this, we then present an optimized approach to CNN evaluation. Finally, we demonstrate the feasibility of our approach by measuring the performance of our scheme on a CNN for classifying the MNIST dataset.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Here, the model denotes the parameters used in the CNN, and like ZEN, vCNN and zkCNN, the structure of the CNN (i.e. the number and different types of CNN layers used) is assumed to be public knowledge.
- 2.
Here, a witness share need not be a share of a secret sharing of a witness.
- 3.
Note that t-zero-knowledge in the presence of semi-honest provers still provides the ordinary zero-knowledge property of a (single-prover) zk-SNARK against a malicious verifier (that does not participate in the proof generation protocol).
- 4.
Note that the order p of \(\mathbb {G}\) is identical to the characteristic of the field \(\mathbb {Z}_p\) which the values in the ABB are elements of. We require p to be of \(2 \lambda \) bits so that the discrete logarithm problem is hard in \(\mathbb {G}\).
- 5.
If a semi-honest MPC protocol for \(\mathcal {F}^{ABB}_{\mathbb {G}}\) is used instead of SPDZ, our protocol is still guaranteed to achieve t-zero-knowledge in the presence of semi-honest parties.
- 6.
The definition of publicly-auditable computation in [34, Appendix D] is for a deterministic functionality.
- 7.
- 8.
- 9.
- 10.
- 11.
MacBook Pro M2 Pro.
References
Ames, S., Hazay, C., Ishai, Y., Venkitasubramaniam, M.: Ligero: lightweight sublinear arguments without a trusted setup. In: Thuraisingham, B.M., Evans, D., Malkin, T., Xu, D. (eds.) ACM CCS 2017, pp. 2087–2104. ACM Press (2017). https://doi.org/10.1145/3133956.3134104
Baum, C., Damgård, I., Orlandi, C.: Publicly auditable secure multi-party computation. In: Abdalla, M., Prisco, R.D. (eds.) SCN 14. LNCS, vol. 8642, pp. 175–196. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10879-7_11
Ben-Sasson, E., Chiesa, A., Riabzev, M., Spooner, N., Virza, M., Ward, N.P.: Aurora: transparent succinct arguments for R1CS. In: Ishai, Y., Rijmen, V. (eds.) EUROCRYPT 2019, Part I. LNCS, vol. 11476, pp. 103–128. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-17653-2_4
Bootle, J., Cerulli, A., Chaidos, P., Groth, J., Petit, C.: Efficient zero-knowledge arguments for arithmetic circuits in the discrete log setting. In: Fischlin, M., Coron, J.S. (eds.) EUROCRYPT 2016, Part II. LNCS, vol. 9666, pp. 327–357. Springer, Cham (2016). https://doi.org/10.1007/978-3-662-49896-5_12
Bourse, F., Minelli, M., Minihold, M., Paillier, P.: Fast homomorphic evaluation of deep discretized neural networks. In: Shacham, H., Boldyreva, A. (eds.) CRYPTO 2018, Part III. LNCS, vol. 10993, pp. 483–512. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-96878-0_17
Bünz, B., Bootle, J., Boneh, D., Poelstra, A., Wuille, P., Maxwell, G.: Bulletproofs: short proofs for confidential transactions and more. In: 2018 IEEE Symposium on Security and Privacy, pp. 315–334. IEEE Computer Society Press (2018). https://doi.org/10.1109/SP.2018.00020
Byali, M., Chaudhari, H., Patra, A., Suresh, A.: FLASH: fast and robust framework for privacy-preserving machine learning. Proc. Privacy Enhanc. Technol. 2020(2), 459–480 (2020). https://doi.org/10.2478/popets-2020-0036
Canetti, R.: Security and composition of multiparty cryptographic protocols. J. Cryptol. 13(1), 143–202 (2000). https://doi.org/10.1007/s001459910006
Chandran, N., Gupta, D., Rastogi, A., Sharma, R., Tripathi, S.: EzPC: programmable, efficient, and scalable secure two-party computation for machine learning. Cryptology ePrint Archive, Report 2017/1109 (2017). https://eprint.iacr.org/2017/1109
Chaudhari, H., Choudhury, A., Patra, A., Suresh, A.: ASTRA: high throughput 3pc over rings with application to secure prediction. In: Sion, R., Papamanthou, C. (eds.) Proceedings of the 2019 ACM SIGSAC Conference on Cloud Computing Security Workshop, CCSW@CCS 2019, London, 11 November 2019, pp. 81–92. ACM (2019). https://doi.org/10.1145/3338466.3358922
Chaudhari, H., Rachuri, R., Suresh, A.: Trident: efficient 4PC framework for privacy preserving machine learning. In: NDSS 2020. The Internet Society (2020)
Chiesa, A., Hu, Y., Maller, M., Mishra, P., Vesely, N., Ward, N.P.: Marlin: preprocessing zkSNARKs with universal and updatable SRS. In: Canteaut, A., Ishai, Y. (eds.) EUROCRYPT 2020, Part I. LNCS, vol. 12105, pp. 738–768. Springer (2020). https://doi.org/10.1007/978-3-030-45721-1_26
Chiesa, A., Ojha, D., Spooner, N.: Fractal: post-quantum and transparent recursive proofs from holography. In: Canteaut, A., Ishai, Y. (eds.) EUROCRYPT 2020, Part I. LNCS, vol. 12105, pp. 769–793. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-45721-1_27
Damgård, I., Nielsen, J.B.: Universally composable efficient multiparty computation from threshold homomorphic encryption. In: Boneh, D. (ed.) CRYPTO 2003. LNCS, vol. 2729, pp. 247–264. Springer, Cham (2003). https://doi.org/10.1007/978-3-540-45146-4_15
Damgård, I., Pastro, V., Smart, N.P., Zakarias, S.: Multiparty computation from somewhat homomorphic encryption. In: Safavi-Naini, R., Canetti, R. (eds.) CRYPTO 2012. LNCS, vol. 7417, pp. 643–662. Springer, Cham (2012). https://doi.org/10.1007/978-3-642-32009-5_38
Dayama, P., Patra, A., Paul, P., Singh, N., Vinayagamurthy, D.: How to prove any NP statement jointly? Efficient distributed-prover zero-knowledge protocols. PoPETs 2022(2), 517–556 (2022). https://doi.org/10.2478/popets-2022-0055
Feng, B., Qin, L., Zhang, Z., Ding, Y., Chu, S.: ZEN: An optimizing compiler for verifiable, zero-knowledge neural network inferences. Cryptology ePrint Archive, Report 2021/087 (2021). https://eprint.iacr.org/2021/087
Gabizon, A., Williamson, Z.J., Ciobotaru, O.: PLONK: permutations over Lagrange-bases for oecumenical noninteractive arguments of knowledge. Cryptology ePrint Archive, Report 2019/953 (2019). https://eprint.iacr.org/2019/953
Gilad-Bachrach, R., Dowlin, N., Laine, K., Lauter, K.E., Naehrig, M., Wernsing, J.: Cryptonets: applying neural networks to encrypted data with high throughput and accuracy. In: Balcan, M., Weinberger, K.Q. (eds.) Proceedings of the 33nd International Conference on Machine Learning, ICML 2016. JMLR Workshop and Conference Proceedings, vol. 48, pp. 201–210. JMLR.org (2016)
Goldreich, O.: Foundations of Cryptography: Basic Applications, vol. 2. Cambridge University Press, Cambridge (2004)
Groth, J.: On the size of pairing-based non-interactive arguments. In: Fischlin, M., Coron, J.S. (eds.) EUROCRYPT 2016, Part II. LNCS, vol. 9666, pp. 305–326. Springer, Heidelberg (2016). https://doi.org/10.1007/978-3-662-49896-5_11
Kang, D., Hashimoto, T., Stoica, I., Sun, Y.: Scaling up trustless DNN inference with zero-knowledge proofs. arXiv preprint arXiv:2210.08674 (2022)
Keller, M., Orsini, E., Scholl, P.: MASCOT: faster malicious arithmetic secure computation with oblivious transfer. In: Weippl, E.R., Katzenbeisser, S., Kruegel, C., Myers, A.C., Halevi, S. (eds.) ACM CCS 2016, pp. 830–842. ACM Press (2016). https://doi.org/10.1145/2976749.2978357
Kitai, H., et al.: MOBIUS: model-oblivious binarized neural networks. IEEE Access 7, 139021–139034 (2019). https://doi.org/10.1109/ACCESS.2019.2939410
Knott, B., Venkataraman, S., Hannun, A.Y., Sengupta, S., Ibrahim, M., van der Maaten, L.: Crypten: secure multi-party computation meets machine learning. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, pp. 4961–4973 (2021)
Koti, N., Pancholi, M., Patra, A., Suresh, A.: SWIFT: super-fast and robust privacy-preserving machine learning. In: Bailey, M., Greenstadt, R. (eds.) USENIX Security 2021, pp. 2651–2668. USENIX Association (2021)
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998). https://doi.org/10.1109/5.726791
Lee, S., Ko, H., Kim, J., Oh, H.: vCNN: verifiable convolutional neural network. Cryptology ePrint Archive, Report 2020/584 (2020). https://eprint.iacr.org/2020/584
Liu, J., Juuti, M., Lu, Y., Asokan, N.: Oblivious neural network predictions via MiniONN transformations. In: Thuraisingham, B.M., Evans, D., Malkin, T., Xu, D. (eds.) ACM CCS 2017, pp. 619–631. ACM Press (2017). https://doi.org/10.1145/3133956.3134056
Liu, T., Xie, X., Zhang, Y.: zkCNN: zero knowledge proofs for convolutional neural network predictions and accuracy. In: Vigna, G., Shi, E. (eds.) ACM CCS 2021, pp. 2968–2985. ACM Press (2021). https://doi.org/10.1145/3460120.3485379
Mohassel, P., Rindal, P.: ABY\(^3\): a mixed protocol framework for machine learning. In: Lie, D., Mannan, M., Backes, M., Wang, X. (eds.) ACM CCS 2018, pp. 35–52. ACM Press (2018). https://doi.org/10.1145/3243734.3243760
Mohassel, P., Zhang, Y.: SecureML: a system for scalable privacy-preserving machine learning. In: 2017 IEEE Symposium on Security and Privacy, pp. 19–38. IEEE Computer Society Press (2017). https://doi.org/10.1109/SP.2017.12
Nishide, T., Ohta, K.: Multiparty computation for interval, equality, and comparison without bit-decomposition protocol. In: Okamoto, T., Wang, X. (eds.) PKC 2007. LNCS, vol. 4450, pp. 343–360. Springer, Cham (2007). https://doi.org/10.1007/978-3-540-71677-8_23
Ozdemir, A., Boneh, D.: Experimenting with collaborative zk-SNARKs: zero-knowledge proofs for distributed secrets. Cryptology ePrint Archive, Report 2021/1530 (2021). https://eprint.iacr.org/2021/1530
Ozdemir, A., Boneh, D.: Experimenting with collaborative zk-SNARKs: zero-knowledge proofs for distributed secrets. In: Butler, K.R.B., Thomas, K. (eds.) USENIX Security 2022, pp. 4291–4308. USENIX Association (2022)
Patra, A., Suresh, A.: BLAZE: Blazing fast privacy-preserving machine learning. In: NDSS 2020. The Internet Society (2020)
Riazi, M.S., Weinert, C., Tkachenko, O., Songhori, E.M., Schneider, T., Koushanfar, F.: Chameleon: a hybrid secure computation framework for machine learning applications. In: Kim, J., Ahn, G.J., Kim, S., Kim, Y., López, J., Kim, T. (eds.) ASIACCS 18, pp. 707–721. ACM Press (2018)
Rouhani, B.D., Riazi, M.S., Koushanfar, F.: Deepsecure: scalable provably-secure deep learning. In: Proceedings of the 55th Annual Design Automation Conference (DAC 2018), pp. 2:1–2:6. ACM (2018). https://doi.org/10.1145/3195970.3196023
Setty, S.: Spartan: efficient and general-purpose zkSNARKs without trusted setup. Cryptology ePrint Archive, Report 2019/550 (2019). https://eprint.iacr.org/2019/550
Smart, N.P., Talibi Alaoui, Y.: Distributing any elliptic curve based protocol. In: Albrecht, M. (ed.) 17th IMA International Conference on Cryptography and Coding. LNCS, vol. 11929, pp. 342–366. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-35199-1_17
Wagh, S., Gupta, D., Chandran, N.: SecureNN: 3-party secure computation for neural network training. PoPETs 2019(3), 26–49 (2019). https://doi.org/10.2478/popets-2019-0035
Weng, J., Weng, J., Tang, G., Yang, A., Li, M., Liu, J.N.: pvcnn: privacy-preserving and verifiable convolutional neural network testing (2022). https://arxiv.org/abs/2201.09186
LeCun, Y., Corinna Cortes, C.J.B.: The ch1MNIST database of handwritten digits (2010). http://yann.lecun.com/exdb/mnist/
Acknowledgement
The authors would like to thank the anonymous referees for their valuable comments and helpful suggestions. This work was partially supported by JST CREST Grant Number JPMJCR22M1 and JSPS KAKENHI Grant Number JP18K18055, Japan.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Attrapadung, N. et al. (2024). Privacy-Preserving Verifiable CNNs. 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_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-54773-7_15
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)