{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T04:04:45Z","timestamp":1748491485921,"version":"3.41.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T00:00:00Z","timestamp":1748390400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T00:00:00Z","timestamp":1748390400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-025-07382-9","type":"journal-article","created":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T11:00:39Z","timestamp":1748430039000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Low-cost ReLU search space compression, replacement, and recovery for efficient private network inference"],"prefix":"10.1007","volume":"81","author":[{"given":"Jingwen","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cuiyun","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiuqing","family":"Mao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,28]]},"reference":[{"key":"7382_CR1","doi-asserted-by":"crossref","unstructured":"Xie Q, Luong M T, Hovy E et al (2020) Self-training with noisy student improves imagenet classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp 10687\u201310698","DOI":"10.1109\/CVPR42600.2020.01070"},{"issue":"18","key":"7382_CR2","doi-asserted-by":"publisher","first-page":"3814","DOI":"10.3390\/math11183814","volume":"11","author":"I Kipyatkova","year":"2023","unstructured":"Kipyatkova I, Kagirov I (2023) Deep models for low-resourced speech recognition: Livvi-Karelian case. Mathematics 11(18):3814","journal-title":"Mathematics"},{"key":"7382_CR3","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1016\/j.ins.2021.12.089","volume":"588","author":"J Wu","year":"2022","unstructured":"Wu J, Xu K, Chen X et al (2022) Price graphs: utilizing the structural information of financial time series for stock prediction. Inf Sci 588:405\u2013424","journal-title":"Inf Sci"},{"key":"7382_CR4","doi-asserted-by":"crossref","unstructured":"Fan Q, Yang J (2018) A denoising autoencoder approach for credit risk analysis. In: Proceedings of the 2018 International Conference on Computing and Artificial Intelligence, 2018, pp 62\u201365","DOI":"10.1145\/3194452.3194456"},{"key":"7382_CR5","doi-asserted-by":"crossref","unstructured":"Boyle E, Gilboa N, Ishai Y (2016) Function secret sharing: improvements and extensions. In: Proceedings of the 2016 ACM SIGSAC conference on computer and communications security, 2016, pp 1292\u20131303","DOI":"10.1145\/2976749.2978429"},{"key":"7382_CR6","unstructured":"Gentry C (2009) A fully homomorphic encryption scheme. Stanford university, 2009"},{"key":"7382_CR7","doi-asserted-by":"crossref","unstructured":"Yao ACC (1986) How to generate and exchange secrets. In: 27th Annual Symposium on Foundations of Computer Science (Sfcs 1986). IEEE, pp 162\u2013167","DOI":"10.1109\/SFCS.1986.25"},{"key":"7382_CR8","doi-asserted-by":"crossref","unstructured":"Bellare M, Hoang VT, Keelveedhi S et al (2013) Efficient garbling from a fixed-key blockcipher. In: 2013 IEEE Symposium on Security and Privacy. IEEE, pp 478\u2013492","DOI":"10.1109\/SP.2013.39"},{"key":"7382_CR9","doi-asserted-by":"crossref","unstructured":"Liu J, Juuti M, Lu Y et al (2017) Oblivious neural network predictions via MiniONN transformations. In: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security. ACM, pp 619\u2013631","DOI":"10.1145\/3133956.3134056"},{"key":"7382_CR10","doi-asserted-by":"crossref","unstructured":"Mishra P, Lehmkuhl R, Srinivasan A et al (2020) Delphi: a cryptographic inference service for neural networks. In: Proceedings of 29th USENIX Security Symposium. USENIX Association, 2020, pp 2505\u20132522","DOI":"10.1145\/3411501.3419418"},{"key":"7382_CR11","unstructured":"Lou Q, Shen Y, Jin H et al (2020) Safenet: a secure, accurate and fast neural network inference. In: International Conference on Learning Representations. 2020"},{"key":"7382_CR12","first-page":"16961","volume":"33","author":"Z Ghodsi","year":"2020","unstructured":"Ghodsi Z, Veldanda AK, Reagen B et al (2020) Cryptonas: private inference on a ReLU budget. Adv Neural Inf Process Syst 33:16961\u201316971","journal-title":"Adv Neural Inf Process Syst"},{"issue":"5","key":"7382_CR13","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/MSEC.2022.3165475","volume":"20","author":"M Cho","year":"2022","unstructured":"Cho M, Ghodsi Z, Reagen B et al (2022) Sphynx: a deep neural network design for private inference. IEEE Secur Priv 20(5):22\u201334","journal-title":"IEEE Secur Priv"},{"key":"7382_CR14","unstructured":"Cho M, Joshi A, Reagen B et al (2022) Selective network linearization for efficient private inference. In: International Conference on Machine Learning. PMLR, 2022, pp 3947\u20133961"},{"key":"7382_CR15","unstructured":"Kundu S, Lu S, Zhang Y, Liu J, Beerel PA (2023) Learning to linearize deep neural networks for secure and efficient private inference. In: International Conference on Learning Representations, 2023"},{"key":"7382_CR16","doi-asserted-by":"crossref","unstructured":"Peng H, Huang S, Zhou T et al (2023) Autorep: automatic relu replacement for fast private network inference. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2023, pp 5178\u20135188","DOI":"10.1109\/ICCV51070.2023.00478"},{"key":"7382_CR17","doi-asserted-by":"publisher","first-page":"120463","DOI":"10.1016\/j.ins.2024.120463","volume":"667","author":"Z Pang","year":"2024","unstructured":"Pang Z, Wang L, Yu F et al (2024) StreamliNet: cost-aware layer-wise neural network linearization for fast and accurate private inference. Inf Sci 667:120463","journal-title":"Inf Sci"},{"key":"7382_CR18","unstructured":"Jha N K, Ghodsi Z, Garg S et al (2021) Deepreduce: ReLU reduction for fast private inference. In: International Conference on Machine Learning. PMLR, 2021, pp 4839\u20134849"},{"key":"7382_CR19","doi-asserted-by":"publisher","first-page":"103156","DOI":"10.1016\/j.sysarc.2024.103156","volume":"152","author":"P Hu","year":"2024","unstructured":"Hu P, Sun L, Hu C et al (2024) DReP: Deep ReLU pruning for fast private inference. J Syst Architect 152:103156","journal-title":"J Syst Architect"},{"issue":"11","key":"7382_CR20","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1145\/359168.359176","volume":"22","author":"A Shamir","year":"1979","unstructured":"Shamir A (1979) How to share a secret. Commun ACM 22(11):612\u2013613","journal-title":"Commun ACM"},{"key":"7382_CR21","doi-asserted-by":"crossref","unstructured":"Blakley GR (1979) Safeguarding cryptographic keys. In: Managing Requirements Knowledge, International Workshop on. IEEE Computer Society, 1979, pp 313\u2013313","DOI":"10.1109\/MARK.1979.8817296"},{"key":"7382_CR22","first-page":"4961","volume":"34","author":"B Knott","year":"2021","unstructured":"Knott B, Venkataraman S, Hannun A et al (2021) Crypten: secure multi-party computation meets machine learning. Adv Neural Inf Process Syst 34:4961\u20134973","journal-title":"Adv Neural Inf Process Syst"},{"key":"7382_CR23","doi-asserted-by":"crossref","unstructured":"Beaver D (1995) Precomputing oblivious transfer. In: Advances in Cryptology\u2014CRYPTO 1995. Springer, Berlin, pp 97\u2013109","DOI":"10.1007\/3-540-44750-4_8"},{"key":"7382_CR24","doi-asserted-by":"crossref","unstructured":"Asharov G, Lindell Y, Schneider T et al (2013) More efficient oblivious transfer and extensions for faster secure computation. In: CCS \u201913: Proceedings of the 2013 ACM SIGSAC Conference on Computer and Communications Security. ACM, New York, pp 535\u2013548","DOI":"10.1145\/2508859.2516738"},{"key":"7382_CR25","unstructured":"Gilad-Bachrach R, Dowlin N, Laine K et al (2016) Cryptonets: applying neural networks to encrypted data with high throughput and accuracy. In: Proceedings of International Conference on Machine Learning. PMLR, 2016, pp 201\u2013210"},{"key":"7382_CR26","doi-asserted-by":"crossref","unstructured":"Boemer F, Lao Y, Cammarota R et al (2019) nGraph-HE: a graph compiler for deep learning on homomorphically encrypted data. In: Proceedings of the 16th ACM International Conference on Computing Frontiers, 2019, pp 3\u201313","DOI":"10.1145\/3310273.3323047"},{"key":"7382_CR27","unstructured":"Zhu Q, Lv X (2018) 2p-dnn: Privacy-preserving deep neural networks based on homomorphic cryptosystem. arXiv preprint arXiv:1807.08459, 2018"},{"issue":"1","key":"7382_CR28","doi-asserted-by":"publisher","first-page":"e13283","DOI":"10.1111\/exsy.13283","volume":"42","author":"A Gopalakrishnan","year":"2025","unstructured":"Gopalakrishnan A, Kulkarni NP, Raghavendra CB et al (2025) PriMed: private federated training and encrypted inference on medical images in healthcare. Expert Syst 42(1):e13283","journal-title":"Expert Syst"},{"key":"7382_CR29","doi-asserted-by":"crossref","unstructured":"Rouhani BD, Riazi MS, Koushanfar F (2018) Deepsecure: Scalable provably-secure deep learning. In: Proceedings of the 55th Annual Design Automation Conference, 2018, pp 1\u20136","DOI":"10.1109\/DAC.2018.8465894"},{"key":"7382_CR30","unstructured":"Mohassel P, Rindal P (2018) ABY3: a mixed protocol framework for machine learning. In: Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security, 2018, pp 35\u201352"},{"key":"7382_CR31","unstructured":"Juvekar C, Vaikuntanathan V, Chandrakasan A (2018) GAZELLE: a low latency framework for secure neural network inference. In: Proceedings of the 27th Security Symposium, 2018, pp1651\u20131669"},{"key":"7382_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2025.108599","volume":"261","author":"Y Bai","year":"2025","unstructured":"Bai Y, Zhao H, Shi X et al (2025) Towards practical and privacy-preserving CNN inference service for cloud-based medical imaging analysis: a homomorphic encryption-based approach. Comput Meth Programs Biomed 261:108599. ISSN 0169-2607","journal-title":"Comput Meth Programs Biomed"},{"key":"7382_CR33","doi-asserted-by":"crossref","unstructured":"Rathee D, Rathee M, Kumar N et al (2020) CrypTFlow2: practical 2-party secure inference. In: Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security. 2020:325\u2013342","DOI":"10.1145\/3372297.3417274"},{"key":"7382_CR34","unstructured":"Huang Z, Lu W j, Hong C et al (2022) Cheetah: lean and fast secure two-party deep neural network inference. In: 31st USENIX Security Symposium, 2022, pp 809\u2013826"},{"key":"7382_CR35","doi-asserted-by":"crossref","unstructured":"Damg\u00e5rd I, Pastro V, Smart N et al (2012) Multiparty computation from somewhat homomorphic encryption. In: Proceedings of Annual Cryptology Conference. Springer, 2012, p 643662","DOI":"10.1007\/978-3-642-32009-5_38"},{"key":"7382_CR36","doi-asserted-by":"crossref","unstructured":"Mohassel P, Zhang Y (2017) Secureml: a system for scalable privacy-preserving machine learning. In: Proceedings of the 2017 IEEE Symposium on Security and Privacy (SP), 2017, pp 19\u201338","DOI":"10.1109\/SP.2017.12"},{"key":"7382_CR37","unstructured":"Maeng K, Suh GE (2023) Approximating ReLU on a Reduced Ring for Efficient MPC-based private inference. arXiv preprint arXiv:2309.04875"},{"key":"7382_CR38","doi-asserted-by":"publisher","first-page":"8472","DOI":"10.1109\/TIFS.2024.3444327","volume":"19","author":"X Yang","year":"2024","unstructured":"Yang X, Chen J, Li Y et al (2024) Fregata: fast private inference with unified secure two-party protocols. IEEE Trans Inf Forensics Secur 19:8472\u20138484","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"7382_CR39","unstructured":"Jha N K, Reagen B (2023) Deepreshape: redesigning neural networks for efficient private inference. arXiv preprint arXiv:2304.10593"},{"issue":"12","key":"7382_CR40","doi-asserted-by":"publisher","first-page":"3519","DOI":"10.1109\/TC.2023.3305754","volume":"72","author":"K Cheng","year":"2023","unstructured":"Cheng K, Xi N, Liu X et al (2023) Private inference for deep neural networks: a secure, adaptive, and efficient realization. IEEE Trans Comput 72(12):3519\u20133531","journal-title":"IEEE Trans Comput"},{"key":"7382_CR41","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"7382_CR42","doi-asserted-by":"crossref","unstructured":"Zagoruyko S, Komodakis N (2016) Wide residual networks. arXiv preprint arXiv:1605.07146","DOI":"10.5244\/C.30.87"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07382-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-025-07382-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07382-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T11:00:57Z","timestamp":1748430057000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-025-07382-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,28]]},"references-count":42,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["7382"],"URL":"https:\/\/doi.org\/10.1007\/s11227-025-07382-9","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,28]]},"assertion":[{"value":"2 May 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"908"}}