{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T07:07:51Z","timestamp":1760425671323,"version":"3.41.0"},"reference-count":49,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2018,9,30]],"date-time":"2018-09-30T00:00:00Z","timestamp":1538265600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1619261"],"award-info":[{"award-number":["CNS-1619261"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Reconfigurable Technol. Syst."],"published-print":{"date-parts":[[2018,9,30]]},"abstract":"<jats:p>\n            Artificial Intelligence (AI) is increasingly incorporated into the\n            <jats:italic>cloud business<\/jats:italic>\n            in order to improve the functionality (e.g., accuracy) of the service. The adoption of AI as a cloud service raises serious privacy concerns in applications where the\n            <jats:italic>risk of data leakage<\/jats:italic>\n            is not acceptable. Examples of such applications include scenarios where clients hold potentially sensitive private information such as medical records, financial data, and\/or location. This article proposes ReDCrypt, the first\n            <jats:italic>reconfigurable<\/jats:italic>\n            hardware-accelerated framework that empowers privacy-preserving inference of deep learning models in cloud servers. ReDCrypt is well-suited for\n            <jats:italic>streaming (a.k.a., real-time AI)<\/jats:italic>\n            settings where clients need to dynamically analyze their data as it is collected over time without having to queue the samples to meet a certain batch size. Unlike prior work, ReDCrypt neither requires to change how AI models are trained nor relies on two non-colluding servers to perform. The privacy-preserving computation in ReDCrypt is executed using\n            <jats:italic>Yao\u2019s Garbled Circuit<\/jats:italic>\n            (GC) protocol. We break down the deep learning inference task into two phases: (i) privacy-insensitive (local) computation, and (ii) privacy-sensitive (interactive) computation. We devise a high-throughput and power-efficient implementation of GC protocol on FPGA for the privacy-sensitive phase. ReDCrypt\u2019s accompanying API provides support for seamless integration of ReDCrypt into any deep learning framework. Proof-of-concept evaluations for different DL applications demonstrate up to 57-fold higher throughput per core compared to the best prior solution with no drop in the accuracy.\n          <\/jats:p>","DOI":"10.1145\/3242899","type":"journal-article","created":{"date-parts":[[2018,12,17]],"date-time":"2018-12-17T13:17:16Z","timestamp":1545052636000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["ReDCrypt"],"prefix":"10.1145","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8412-4320","authenticated-orcid":false,"given":"Bita Darvish","family":"Rouhani","sequence":"first","affiliation":[{"name":"University of California San Diego, Gilman Dr, La Jolla, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siam Umar","family":"Hussain","sequence":"additional","affiliation":[{"name":"University of California San Diego, Gilman Dr, La Jolla, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kristin","family":"Lauter","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Farinaz","family":"Koushanfar","sequence":"additional","affiliation":[{"name":"University of California San Diego, Gilman Dr, La Jolla, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,12,15]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1561\/2000000039"},{"key":"e_1_2_1_2_1","volume-title":"Deep learning. Nature 521, 7553","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun , Yoshua Bengio , and Geoffrey Hinton . 2015. Deep learning. Nature 521, 7553 ( 2015 ), 436. Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature 521, 7553 (2015), 436."},{"key":"e_1_2_1_3_1","volume-title":"The learning machines. Nature 505, 7482","author":"Nicola Joneset","year":"2014","unstructured":"Nicola Joneset al. 2014. The learning machines. Nature 505, 7482 ( 2014 ), 146--148. Nicola Joneset al. 2014. The learning machines. Nature 505, 7482 (2014), 146--148."},{"key":"e_1_2_1_4_1","unstructured":"Jeremy Kirk. 2016. IBM join forces to build a brain-like computer. Retrieved from http:\/\/www.pcworld.com\/article\/2051501\/universities-join-ibm-in-cognitive-computing-researchproject.html.  Jeremy Kirk. 2016. IBM join forces to build a brain-like computer. Retrieved from http:\/\/www.pcworld.com\/article\/2051501\/universities-join-ibm-in-cognitive-computing-researchproject.html."},{"key":"e_1_2_1_5_1","volume-title":"Proceedings of the 33rd International Conference on Machine Learning. 201--210","author":"Gilad-Bachrach Ran","year":"2016","unstructured":"Ran Gilad-Bachrach , Nathan Dowlin , Kim Laine , Kristin Lauter , Michael Naehrig , and John Wernsing . 2016 . CryptoNets: Applying neural networks to encrypted data with high throughput and accuracy . In Proceedings of the 33rd International Conference on Machine Learning. 201--210 . Ran Gilad-Bachrach, Nathan Dowlin, Kim Laine, Kristin Lauter, Michael Naehrig, and John Wernsing. 2016. CryptoNets: Applying neural networks to encrypted data with high throughput and accuracy. In Proceedings of the 33rd International Conference on Machine Learning. 201--210."},{"key":"e_1_2_1_6_1","first-page":"396","article-title":"SecureML: A system for scalable privacy-preserving machine learning","volume":"2017","author":"Mohassel Payman","year":"2017","unstructured":"Payman Mohassel and Yupeng Zhang . 2017 . SecureML: A system for scalable privacy-preserving machine learning . IACR Cryptology ePrint Archive 2017 (2017), 396 . Payman Mohassel and Yupeng Zhang. 2017. SecureML: A system for scalable privacy-preserving machine learning. IACR Cryptology ePrint Archive 2017 (2017), 396.","journal-title":"IACR Cryptology ePrint Archive"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/1881511.1881546"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2898027"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021746"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2015.32"},{"volume-title":"Secure computation of MIPS machine code","author":"Wang Xiao","key":"e_1_2_1_11_1","unstructured":"Xiao Wang , S. Dov Gordon , Allen McIntosh , and Jonathan Katz . 2016. Secure computation of MIPS machine code . In ESORICS. Springer . Xiao Wang, S. Dov Gordon, Allen McIntosh, and Jonathan Katz. 2016. Secure computation of MIPS machine code. In ESORICS. Springer."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00145-004-0102-6"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1986.25"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2013.39"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/100216.100287"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/336992.337028"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-70583-3_40"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-46803-6_8"},{"key":"e_1_2_1_19_1","first-page":"145","article-title":"Extending oblivious transfers efficiently","volume":"2729","author":"Ishai Yuval","year":"2003","unstructured":"Yuval Ishai , Joe Kilian , Kobbi Nissim , and Erez Petrank . 2003 . Extending oblivious transfers efficiently . In Crypto , Vol. 2729. Spring er, 145 -- 161 . Yuval Ishai, Joe Kilian, Kobbi Nissim, and Erez Petrank. 2003. Extending oblivious transfers efficiently. In Crypto, Vol. 2729. Springer, 145--161.","journal-title":"Crypto"},{"key":"e_1_2_1_20_1","volume-title":"PCF: A portable circuit format for scalable two-party secure computation. In Presented as Part of the 22nd USENIX Security Symposium (USENIX Security 13). 321--336.","author":"Kreuter Ben","year":"2013","unstructured":"Ben Kreuter , Abhi Shelat , Benjamin Mood , and Kevin Butler . 2013 . PCF: A portable circuit format for scalable two-party secure computation. In Presented as Part of the 22nd USENIX Security Symposium (USENIX Security 13). 321--336. Ben Kreuter, Abhi Shelat, Benjamin Mood, and Kevin Butler. 2013. PCF: A portable circuit format for scalable two-party secure computation. In Presented as Part of the 22nd USENIX Security Symposium (USENIX Security 13). 321--336."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72540-4_4"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00457-5_22"},{"volume-title":"EUROCRYPT\u201911 (LNCS)","author":"Shelat Abhi","key":"e_1_2_1_23_1","unstructured":"Abhi Shelat and Chih-hao Shen. 2011. Two-output secure computation with malicious adversaries . In EUROCRYPT\u201911 (LNCS) , Vol. 6632 . Springer , 386--405. Abhi Shelat and Chih-hao Shen. 2011. Two-output secure computation with malicious adversaries. In EUROCRYPT\u201911 (LNCS), Vol. 6632. Springer, 386--405."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00145-011-9107-0"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2382196.2382279"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934583.2934644"},{"key":"e_1_2_1_27_1","volume-title":"Computation error analysis of block floating point arithmetic oriented convolution neural network accelerator design. arXiv preprint arXiv:1709.07776","author":"Song Zhourui","year":"2017","unstructured":"Zhourui Song , Zhenyu Liu , Chunlu Wang , and Dongsheng Wang . 2017. Computation error analysis of block floating point arithmetic oriented convolution neural network accelerator design. arXiv preprint arXiv:1709.07776 ( 2017 ). Zhourui Song, Zhenyu Liu, Chunlu Wang, and Dongsheng Wang. 2017. Computation error analysis of block floating point arithmetic oriented convolution neural network accelerator design. arXiv preprint arXiv:1709.07776 (2017)."},{"key":"e_1_2_1_28_1","volume-title":"Fastplay\u2014A parallelization model and implementation of SMC on CUDA based GPU cluster architecture. IACR Cryptology ePrint Archive","author":"Pu Shi","year":"2011","unstructured":"Shi Pu , Pu Duan , and Jyh-Charn Liu . 2011. Fastplay\u2014A parallelization model and implementation of SMC on CUDA based GPU cluster architecture. IACR Cryptology ePrint Archive ( 2011 ). Shi Pu, Pu Duan, and Jyh-Charn Liu. 2011. Fastplay\u2014A parallelization model and implementation of SMC on CUDA based GPU cluster architecture. IACR Cryptology ePrint Archive (2011)."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2523649.2523681"},{"key":"e_1_2_1_30_1","unstructured":"XILLYBUS. 2017. Retrieved from http:\/\/xillybus.com\/.  XILLYBUS. 2017. Retrieved from http:\/\/xillybus.com\/."},{"key":"e_1_2_1_31_1","unstructured":"Joan Daemen and Vincent Rijmen. 2013. The Rijndael Block Cipher.  Joan Daemen and Vincent Rijmen. 2013. The Rijndael Block Cipher."},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1155\/2009\/501672"},{"key":"e_1_2_1_34_1","unstructured":"Yann LeCun Corinna Cortes and Christopher Burges. 2017. MNIST dataset. Retrieved from http:\/\/yann.lecun.com\/exdb\/mnist\/.  Yann LeCun Corinna Cortes and Christopher Burges. 2017. MNIST dataset. Retrieved from http:\/\/yann.lecun.com\/exdb\/mnist\/."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_1_36_1","unstructured":"UCI machine learning repository. 2017. UCI machine learning repository: ISOLET data set. Retrieved from https:\/\/archive.ics.uci.edu\/ml\/datasets\/isolet.  UCI machine learning repository. 2017. UCI machine learning repository: ISOLET data set. Retrieved from https:\/\/archive.ics.uci.edu\/ml\/datasets\/isolet."},{"key":"e_1_2_1_37_1","unstructured":"UCI machine learning repository. 2017. UCI machine learning repository: Daily and sports activities data set. Retrieved from https:\/\/archive.ics.uci.edu\/ml\/datasets\/Daily+and+ Sports+Activities.  UCI machine learning repository. 2017. UCI machine learning repository: Daily and sports activities data set. Retrieved from https:\/\/archive.ics.uci.edu\/ml\/datasets\/Daily+and+ Sports+Activities."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508859.2516751"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-07536-5_33"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2660267.2660365"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2013.30"},{"key":"e_1_2_1_42_1","volume-title":"Korajczyk","author":"Connor Gregory","year":"2010","unstructured":"Gregory Connor , Lisa R. Goldberg , and Robert A . Korajczyk . 2010 . Portfolio Risk Analysis. Princeton University Press . Gregory Connor, Lisa R. Goldberg, and Robert A. Korajczyk. 2010. Portfolio Risk Analysis. Princeton University Press."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078155.3078161"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/1161366.1161393"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1186\/1687-417X-2007-037343"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-09699-5_3"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134056"},{"key":"e_1_2_1_48_1","volume-title":"DeepSecure: Scalable provably-secure deep learning. arXiv preprint arXiv:1705.08963","author":"Rouhani Bita Darvish","year":"2017","unstructured":"Bita Darvish Rouhani , M. Sadegh Riazi , and Farinaz Koushanfar . 2017. DeepSecure: Scalable provably-secure deep learning. arXiv preprint arXiv:1705.08963 ( 2017 ). Bita Darvish Rouhani, M. Sadegh Riazi, and Farinaz Koushanfar. 2017. DeepSecure: Scalable provably-secure deep learning. arXiv preprint arXiv:1705.08963 (2017)."},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2012.25"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196074"}],"container-title":["ACM Transactions on Reconfigurable Technology and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3242899","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3242899","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3242899","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:39:24Z","timestamp":1750210764000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3242899"}},"subtitle":["Real-Time Privacy-Preserving Deep Learning Inference in Clouds Using FPGAs"],"short-title":[],"issued":{"date-parts":[[2018,9,30]]},"references-count":49,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2018,9,30]]}},"alternative-id":["10.1145\/3242899"],"URL":"https:\/\/doi.org\/10.1145\/3242899","relation":{},"ISSN":["1936-7406","1936-7414"],"issn-type":[{"type":"print","value":"1936-7406"},{"type":"electronic","value":"1936-7414"}],"subject":[],"published":{"date-parts":[[2018,9,30]]},"assertion":[{"value":"2017-12-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-07-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-12-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}