{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T03:37:32Z","timestamp":1772077052569,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":76,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,3,9]],"date-time":"2020-03-09T00:00:00Z","timestamp":1583712000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-17-1-0274"],"award-info":[{"award-number":["FA9550-17-1-0274"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["FA8650-20-2-7009, R0011-18-C-0020"],"award-info":[{"award-number":["FA8650-20-2-7009, R0011-18-C-0020"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000093","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01EB028350"],"award-info":[{"award-number":["R01EB028350"]}],"id":[{"id":"10.13039\/100000093","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS#1703812, ECCS#1609823, CCF#1553192"],"award-info":[{"award-number":["CNS#1703812, ECCS#1609823, CCF#1553192"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,3,9]]},"DOI":"10.1145\/3373376.3378522","type":"proceedings-article","created":{"date-parts":[[2020,3,13]],"date-time":"2020-03-13T22:37:01Z","timestamp":1584139021000},"page":"3-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":61,"title":["Shredder"],"prefix":"10.1145","author":[{"given":"Fatemehsadat","family":"Mireshghallah","sequence":"first","affiliation":[{"name":"University of California, San Diego, La Jolla, CA, USA"}]},{"given":"Mohammadkazem","family":"Taram","sequence":"additional","affiliation":[{"name":"University of California, San Diego, La Jolla, CA, USA"}]},{"given":"Prakash","family":"Ramrakhyani","sequence":"additional","affiliation":[{"name":"ARM, Inc., Austin, TX, USA"}]},{"given":"Ali","family":"Jalali","sequence":"additional","affiliation":[{"name":"Amazon.com, Inc., Ausitn, TX, USA"}]},{"given":"Dean","family":"Tullsen","sequence":"additional","affiliation":[{"name":"University of California, San Diego, La Jolla, CA, USA"}]},{"given":"Hadi","family":"Esmaeilzadeh","sequence":"additional","affiliation":[{"name":"University of California, San Diego, La Jolla, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2020,3,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1721654.1721667"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1556154.1556173"},{"issue":"4","key":"e_1_3_2_1_3_1","first-page":"1","article-title":"Outsourcing business to cloud computing services: Opportunities and challenges","volume":"10","author":"Motahari-Nezhad H. R.","year":"2009","unstructured":"H. R. Motahari-Nezhad , B. Stephenson , and S. Singhal , \u201c Outsourcing business to cloud computing services: Opportunities and challenges ,\u201d IEEE Internet Computing , vol. 10 , no. 4 , pp. 1 -- 17 , 2009 . H. R. Motahari-Nezhad, B. Stephenson, and S. Singhal, \u201cOutsourcing business to cloud computing services: Opportunities and challenges,\u201d IEEE Internet Computing, vol. 10, no. 4, pp. 1--17, 2009.","journal-title":"IEEE Internet Computing"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaa8415"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2011.77"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694347"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00002"},{"key":"e_1_3_2_1_9_1","volume-title":"27th USENIX Security Symposium (USENIX Security 18)","author":"Lipp M.","year":"2018","unstructured":"M. Lipp , M. Schwarz , D. Gruss , T. Prescher , W. Haas , A. Fogh , J. Horn , S. Mangard , P. Kocher , D. Genkin , Y. Yarom , and M. Hamburg , \u201c Meltdown: Reading kernel memory from user space ,\u201d in 27th USENIX Security Symposium (USENIX Security 18) , 2018 . M. Lipp, M. Schwarz, D. Gruss, T. Prescher, W. Haas, A. Fogh, J. Horn, S. Mangard, P. Kocher, D. Genkin, Y. Yarom, and M. Hamburg, \u201cMeltdown: Reading kernel memory from user space,\u201d in 27th USENIX Security Symposium (USENIX Security 18), 2018."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1653662.1653687"},{"key":"e_1_3_2_1_11_1","volume-title":"Facebook data harvesting scandal widens to 87 million people","year":"2019","unstructured":"NBCNews) , \u201c Facebook data harvesting scandal widens to 87 million people .\u201d online accessed May 2019 https:\/\/www.nbcnews.com\/tech\/tech-news\/facebook-data-harvesting-scandal-widens-87-million-people-n862771. NBCNews), \u201cFacebook data harvesting scandal widens to 87 million people.\u201d online accessed May 2019 https:\/\/www.nbcnews.com\/tech\/tech-news\/facebook-data-harvesting-scandal-widens-87-million-people-n862771."},{"key":"e_1_3_2_1_12_1","volume-title":"23andme scandal highlights data privacy concerns shared by axonium and mr koh boon hwee","year":"2019","unstructured":"Axonium) , \u201c 23andme scandal highlights data privacy concerns shared by axonium and mr koh boon hwee ..\u201d online accessed May 2019 https:\/\/medium.com\/@Axonium_org\/23andme-scandal-highlights-data-privacy-concerns-shared-by-axonium-and-mr-koh-boon-hwee-dd2e241f1ef2. Axonium), \u201c23andme scandal highlights data privacy concerns shared by axonium and mr koh boon hwee..\u201d online accessed May 2019 https:\/\/medium.com\/@Axonium_org\/23andme-scandal-highlights-data-privacy-concerns-shared-by-axonium-and-mr-koh-boon-hwee-dd2e241f1ef2."},{"key":"e_1_3_2_1_13_1","volume-title":"NIPS Workshop on Private Multi-Party Machine Learning","author":"Konen\u00fd J.","year":"2016","unstructured":"J. Konen\u00fd , H. B. McMahan , F. X. Yu , P. Richtarik , A. T. Suresh , and D. Bacon , \u201c Federated learning: Strategies for improving communication efficiency ,\u201d in NIPS Workshop on Private Multi-Party Machine Learning , 2016 . J. Konen\u00fd, H. B. McMahan, F. X. Yu, P. Richtarik, A. T. Suresh, and D. Bacon, \u201cFederated learning: Strategies for improving communication efficiency,\u201d in NIPS Workshop on Private Multi-Party Machine Learning, 2016."},{"key":"e_1_3_2_1_14_1","volume-title":"Apple, 2017","author":"Team Differential Privacy","year":"2019","unstructured":"relax Differential Privacy Team , \u201c Learning with privacy at scale,\u201d tech. rep ., Apple, 2017 . online accessed May 2019 https:\/\/machinelearning.apple.com\/docs\/learning-with-privacy-at-scale\/appledifferentialprivacysystem.pdf. relax Differential Privacy Team, \u201cLearning with privacy at scale,\u201d tech. rep., Apple, 2017. online accessed May 2019 https:\/\/machinelearning.apple.com\/docs\/learning-with-privacy-at-scale\/appledifferentialprivacysystem.pdf."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2660267.2660348"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1986.25"},{"key":"e_1_3_2_1_17_1","first-page":"1057","article-title":"Secure multiparty computation from sgx","volume":"2016","author":"Bahmani R.","year":"2016","unstructured":"R. Bahmani , M. Barbosa , F. Brasser , B. Portela , A.-R. Sadeghi , G. Scerri , and B. Warinschi , \u201c Secure multiparty computation from sgx ,\u201d IACR Cryptology ePrint Archive , vol. 2016 , p. 1057 , 2016 . R. Bahmani, M. Barbosa, F. Brasser, B. Portela, A.-R. Sadeghi, G. Scerri, and B. Warinschi, \u201cSecure multiparty computation from sgx,\u201d IACR Cryptology ePrint Archive, vol. 2016, p. 1057, 2016.","journal-title":"IACR Cryptology ePrint Archive"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1536414.1536440"},{"key":"e_1_3_2_1_19_1","first-page":"201","volume-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning -","volume":"48","author":"Dowlin N.","year":"2016","unstructured":"N. Dowlin , R. Gilad-Bachrach , K. Laine , K. Lauter , M. Naehrig , and J. Wernsing , \u201c Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy ,\u201d in Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48 , ICML'16, pp. 201 -- 210 , JMLR.org, 2016 . N. Dowlin, R. Gilad-Bachrach, K. Laine, K. Lauter, M. Naehrig, and J. Wernsing, \u201cCryptonets: Applying neural networks to encrypted data with high throughput and accuracy,\u201d in Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48, ICML'16, pp. 201--210, JMLR.org, 2016."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-45239-0_4"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134056"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/11681878_14"},{"key":"e_1_3_2_1_24_1","volume-title":"Bell system technical journal","author":"Shannon C. E.","unstructured":"C. E. Shannon , \u201c A mathematical theory of communication ,\u201d Bell system technical journal , vol. 27 , no. 3, pp. 379--423, 1948. C. E. Shannon, \u201cA mathematical theory of communication,\u201d Bell system technical journal, vol. 27, no. 3, pp. 379--423, 1948."},{"key":"e_1_3_2_1_25_1","volume-title":"NIPS","author":"Yosinski J.","year":"2014","unstructured":"J. Yosinski , J. Clune , Y. Bengio , and H. Lipson , \u201c How transferable are features in deep neural networks? ,\u201d in NIPS , 2014 . J. Yosinski, J. Clune, Y. Bengio, and H. Lipson, \u201cHow transferable are features in deep neural networks?,\u201d in NIPS, 2014."},{"key":"e_1_3_2_1_26_1","volume-title":"Opening the black box of deep neural networks via information","author":"Shwartz-Ziv R.","year":"2017","unstructured":"R. Shwartz-Ziv and N. Tishby , \u201c Opening the black box of deep neural networks via information ,\u201d 2017 . R. Shwartz-Ziv and N. Tishby, \u201cOpening the black box of deep neural networks via information,\u201d 2017."},{"key":"e_1_3_2_1_27_1","volume-title":"Estimating information flow in neural networks","author":"Goldfeld Z.","year":"2018","unstructured":"Z. Goldfeld , E. van den Berg , K. Greenewald , I. Melnyk , N. Nguyen , B. Kingsbury , and Y. Polyanskiy , \u201c Estimating information flow in neural networks ,\u201d 2018 . Z. Goldfeld, E. van den Berg, K. Greenewald, I. Melnyk, N. Nguyen, B. Kingsbury, and Y. Polyanskiy, \u201cEstimating information flow in neural networks,\u201d 2018."},{"key":"e_1_3_2_1_28_1","volume-title":"International Conference on Learning Representations","author":"Saxe A. M.","year":"2018","unstructured":"A. M. Saxe , Y. Bansal , J. Dapello , M. Advani , A. Kolchinsky , B. D. Tracey , and D. D. Cox , \u201c On the information bottleneck theory of deep learning ,\u201d in International Conference on Learning Representations , 2018 . A. M. Saxe, Y. Bansal, J. Dapello, M. Advani, A. Kolchinsky, B. D. Tracey, and D. D. Cox, \u201cOn the information bottleneck theory of deep learning,\u201d in International Conference on Learning Representations, 2018."},{"key":"e_1_3_2_1_29_1","volume-title":"The information bottleneck method","author":"Tishby N.","year":"2000","unstructured":"N. Tishby , F. C. Pereira , and W. Bialek , \u201c The information bottleneck method ,\u201d arXiv preprint physics\/0004057, 2000 . N. Tishby, F. C. Pereira, and W. Bialek, \u201cThe information bottleneck method,\u201d arXiv preprint physics\/0004057, 2000."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2584610"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2017.2779108"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2013.2253320"},{"key":"e_1_3_2_1_34_1","first-page":"719","volume-title":"Proceedings. International Symposium on Information Theory, 2005. ISIT 2005.","author":"Guo D.","year":"2005","unstructured":"D. Guo , S. Shamai , and S. Verd\u00fa , \u201c Additive non-gaussian noise channels: Mutual information and conditional mean estimation ,\u201d in Proceedings. International Symposium on Information Theory, 2005. ISIT 2005. , pp. 719 -- 723 , IEEE, 2005 . D. Guo, S. Shamai, and S. Verd\u00fa, \u201cAdditive non-gaussian noise channels: Mutual information and conditional mean estimation,\u201d in Proceedings. International Symposium on Information Theory, 2005. ISIT 2005., pp. 719--723, IEEE, 2005."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2005.844072"},{"key":"e_1_3_2_1_36_1","first-page":"00149","article-title":"Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding","volume":"1510","author":"Han S.","year":"2016","unstructured":"S. Han , H. Mao , and W. J. Dally , \u201c Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding ,\u201d CoRR , vol. abs\/ 1510 . 00149 , 2016 . S. Han, H. Mao, and W. J. Dally, \u201cDeep compression: Compressing deep neural network with pruning, trained quantization and huffman coding,\u201d CoRR, vol. abs\/1510.00149, 2016.","journal-title":"CoRR"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366231.2337200"},{"key":"e_1_3_2_1_38_1","first-page":"05350","article-title":"regularization versus batch and weight normalization","volume":"1706","author":"van Laarhoven T.","year":"2017","unstructured":"T. van Laarhoven , \u201cL2 regularization versus batch and weight normalization ,\u201d CoRR , vol. abs\/ 1706 . 05350 , 2017 . T. van Laarhoven, \u201cL2 regularization versus batch and weight normalization,\u201d CoRR, vol. abs\/1706.05350, 2017.","journal-title":"CoRR"},{"key":"e_1_3_2_1_39_1","first-page":"6980","article-title":"Adam: A method for stochastic optimization","volume":"1412","author":"Kingma D. P.","year":"2015","unstructured":"D. P. Kingma and J. Ba , \u201c Adam: A method for stochastic optimization ,\u201d CoRR , vol. abs\/ 1412 . 6980 , 2015 . D. P. Kingma and J. Ba, \u201cAdam: A method for stochastic optimization,\u201d CoRR, vol. abs\/1412.6980, 2015.","journal-title":"CoRR"},{"key":"e_1_3_2_1_40_1","volume-title":"The 20 newsgroups data set","year":"2019","unstructured":"\u201c The 20 newsgroups data set .\u201d online accessed July 2019 http:\/\/qwone.com\/ jason\/20Newsgroups\/. \u201cThe 20 newsgroups data set.\u201d online accessed July 2019 http:\/\/qwone.com\/ jason\/20Newsgroups\/."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"e_1_3_2_1_42_1","first-page":"1","article-title":"Deep private-feature extraction","author":"Osia S. A.","year":"2018","unstructured":"S. A. Osia , A. Taheri , A. S. Shamsabadi , M. Katevas , H. Haddadi , and H. R. R. Rabiee , \u201c Deep private-feature extraction ,\u201d IEEE Transactions on Knowledge and Data Engineering , pp. 1 -- 1 , 2018 . S. A. Osia, A. Taheri, A. S. Shamsabadi, M. Katevas, H. Haddadi, and H. R. R. Rabiee, \u201cDeep private-feature extraction,\u201d IEEE Transactions on Knowledge and Data Engineering, pp. 1--1, 2018.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037698"},{"key":"e_1_3_2_1_44_1","volume-title":"Online accessed","year":"2019","unstructured":"\u201c Apple moves to third-generation siri back-end, built on opensource mesos platform .\u201d Online accessed August 2019 , https:\/\/9to5mac.com\/2015\/04\/27\/siri-backend-mesos\/. \u201cApple moves to third-generation siri back-end, built on opensource mesos platform.\u201d Online accessed August 2019, https:\/\/9to5mac.com\/2015\/04\/27\/siri-backend-mesos\/."},{"key":"e_1_3_2_1_45_1","volume-title":"Online accessed","year":"2019","unstructured":"\u201c Apple moves to third-generation siri back-end, built on opensource mesos platform .\u201d Online accessed August 2019 , https:\/\/9to5mac.com\/2015\/04\/27\/siri-backend-mesos\/. \u201cApple moves to third-generation siri back-end, built on opensource mesos platform.\u201d Online accessed August 2019, https:\/\/9to5mac.com\/2015\/04\/27\/siri-backend-mesos\/."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2627444"},{"key":"e_1_3_2_1_47_1","volume-title":"The mnist dataset of handwritten digits","author":"N. Yann LeCun (Courant Institute and N. Y. Corinna Cortes (Google Labs","year":"2019","unstructured":"N. Yann LeCun (Courant Institute and N. Y. Corinna Cortes (Google Labs , \u201c The mnist dataset of handwritten digits .\u201d online accessed May 2019 http:\/\/www.pymvpa.org\/datadb\/mnist.html. N. Yann LeCun (Courant Institute and N. Y. Corinna Cortes (Google Labs, \u201cThe mnist dataset of handwritten digits.\u201d online accessed May 2019 http:\/\/www.pymvpa.org\/datadb\/mnist.html."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_49_1","volume-title":"Convolutional deep belief networks on cifar-10","author":"Krizhevsky A.","year":"2010","unstructured":"A. Krizhevsky , \u201c Convolutional deep belief networks on cifar-10 ,\u201d 2010 . A. Krizhevsky, \u201cConvolutional deep belief networks on cifar-10,\u201d 2010."},{"key":"e_1_3_2_1_50_1","first-page":"6082","article-title":"Multi-digit number recognition from street view imagery using deep convolutional neural networks","volume":"1312","author":"Goodfellow I. J.","year":"2014","unstructured":"I. J. Goodfellow , Y. Bulatov , J. Ibarz , S. Arnoud , and V. D. Shet , \u201c Multi-digit number recognition from street view imagery using deep convolutional neural networks ,\u201d CoRR , vol. abs\/ 1312 . 6082 , 2014 . I. J. Goodfellow, Y. Bulatov, J. Ibarz, S. Arnoud, and V. D. Shet, \u201cMulti-digit number recognition from street view imagery using deep convolutional neural networks,\u201d CoRR, vol. abs\/1312.6082, 2014.","journal-title":"CoRR"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_1_53_1","volume-title":"ICML","author":"Coates A.","year":"2013","unstructured":"A. Coates , B. Huval , T. Wang , D. J. Wu , B. Catanzaro , and A. Y. Ng , \u201c Deep learning with cots hpc systems ,\u201d in ICML , 2013 . A. Coates, B. Huval, T. Wang, D. J. Wu, B. Catanzaro, and A. Y. Ng, \u201cDeep learning with cots hpc systems,\u201d in ICML, 2013."},{"key":"e_1_3_2_1_54_1","first-page":"11008","article-title":"Security risks in deep learning implementations","volume":"1711","author":"Xiao Q.","year":"2017","unstructured":"Q. Xiao , K. Li , D. Zhang , and W. Xu , \u201c Security risks in deep learning implementations ,\u201d CoRR , vol. abs\/ 1711 . 11008 , 2017 . Q. Xiao, K. Li, D. Zhang, and W. Xu, \u201cSecurity risks in deep learning implementations,\u201d CoRR, vol. abs\/1711.11008, 2017.","journal-title":"CoRR"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2015.7447103"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1561\/0400000042"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/11761679_29"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220106"},{"key":"e_1_3_2_1_61_1","volume-title":"A hybrid deep learning architecture for privacy-preserving mobile analytics","author":"Osia S. A.","year":"2017","unstructured":"S. A. Osia , A. S. Shamsabadi , S. Sajadmanesh , A. Taheri , K. Katevas , H. R. Rabiee , N. D. Lane , and H. Haddadi , \u201c A hybrid deep learning architecture for privacy-preserving mobile analytics ,\u201d 2017 . S. A. Osia, A. S. Shamsabadi, S. Sajadmanesh, A. Taheri, K. Katevas, H. R. Rabiee, N. D. Lane, and H. Haddadi, \u201cA hybrid deep learning architecture for privacy-preserving mobile analytics,\u201d 2017."},{"key":"e_1_3_2_1_62_1","first-page":"12024","article-title":"Privacy aware offloading of deep neural networks","volume":"1805","author":"Leroux S.","year":"2018","unstructured":"S. Leroux , T. Verbelen , P. Simoens , and B. Dhoedt , \u201c Privacy aware offloading of deep neural networks ,\u201d CoRR , vol. abs\/ 1805 . 12024 , 2018 . S. Leroux, T. Verbelen, P. Simoens, and B. Dhoedt, \u201cPrivacy aware offloading of deep neural networks,\u201d CoRR, vol. abs\/1805.12024, 2018.","journal-title":"CoRR"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487726.2488368"},{"key":"e_1_3_2_1_64_1","volume-title":"Trustzone: Integrated hardware and software security","author":"Alves T.","year":"2004","unstructured":"T. Alves and D. Felton , \u201c Trustzone: Integrated hardware and software security ,\u201d 01 2004 . T. Alves and D. Felton, \u201cTrustzone: Integrated hardware and software security,\u201d 01 2004."},{"key":"e_1_3_2_1_65_1","volume-title":"International Conference on Learning Representations","author":"Tramer F.","year":"2019","unstructured":"F. Tramer and D. Boneh , \u201c Slalom: Fast, verifiable and private execution of neural networks in trusted hardware ,\u201d in International Conference on Learning Representations , 2019 . F. Tramer and D. Boneh, \u201cSlalom: Fast, verifiable and private execution of neural networks in trusted hardware,\u201d in International Conference on Learning Representations, 2019."},{"key":"e_1_3_2_1_66_1","volume-title":"Chiron: Privacy-preserving machine learning as a service","author":"Hunt T.","year":"2018","unstructured":"T. Hunt , C. Song , R. Shokri , V. Shmatikov , and E. Witchel , \u201c Chiron: Privacy-preserving machine learning as a service ,\u201d 2018 . T. Hunt, C. Song, R. Shokri, V. Shmatikov, and E. Witchel, \u201cChiron: Privacy-preserving machine learning as a service,\u201d 2018."},{"key":"e_1_3_2_1_67_1","volume-title":"Mlcapsule: Guarded offline deployment of machine learning as a service","author":"Hanzlik L.","year":"2018","unstructured":"L. Hanzlik , Y. Zhang , K. Grosse , A. Salem , M. Augustin , M. Backes , and M. Fritz , \u201c Mlcapsule: Guarded offline deployment of machine learning as a service ,\u201d 2018 . L. Hanzlik, Y. Zhang, K. Grosse, A. Salem, M. Augustin, M. Backes, and M. Fritz, \u201cMlcapsule: Guarded offline deployment of machine learning as a service,\u201d 2018."},{"key":"e_1_3_2_1_68_1","first-page":"619","volume-title":"25th USENIX Security Symposium (USENIX Security 16)","author":"Ohrimenko O.","year":"2016","unstructured":"O. Ohrimenko , F. Schuster , C. Fournet , A. Mehta , S. Nowozin , K. Vaswani , and M. Costa , \u201c Oblivious multi-party machine learning on trusted processors ,\u201d in 25th USENIX Security Symposium (USENIX Security 16) , (Austin, TX), pp. 619 -- 636 , USENIX Association , 2016 . O. Ohrimenko, F. Schuster, C. Fournet, A. Mehta, S. Nowozin, K. Vaswani, and M. Costa, \u201cOblivious multi-party machine learning on trusted processors,\u201d in 25th USENIX Security Symposium (USENIX Security 16), (Austin, TX), pp. 619--636, USENIX Association, 2016."},{"key":"e_1_3_2_1_69_1","volume-title":"ZombieLoad: Cross-privilege-boundary data sampling","author":"Schwarz M.","year":"1905","unstructured":"M. Schwarz , M. Lipp , D. Moghimi , J. Van Bulck , J. Stecklina , T. Prescher , and D. Gruss , \u201c ZombieLoad: Cross-privilege-boundary data sampling ,\u201d arXiv: 1905 .05726, 2019. M. Schwarz, M. Lipp, D. Moghimi, J. Van Bulck, J. Stecklina, T. Prescher, and D. Gruss, \u201cZombieLoad: Cross-privilege-boundary data sampling,\u201d arXiv:1905.05726, 2019."},{"key":"e_1_3_2_1_70_1","volume-title":"Proceedings of the 27th USENIX Security Symposium, USENIX Association","author":"Bulck J. Van","year":"2018","unstructured":"J. Van Bulck , M. Minkin , O. Weisse , D. Genkin , B. Kasikci , F. Piessens , M. Silberstein , T. F. Wenisch , Y. Yarom , and R. Strackx , \u201c Foreshadow: Extracting the keys to the Intel SGX kingdom with transient out-of-order execution ,\u201d in Proceedings of the 27th USENIX Security Symposium, USENIX Association , August 2018 . J. Van Bulck, M. Minkin, O. Weisse, D. Genkin, B. Kasikci, F. Piessens, M. Silberstein, T. F. Wenisch, Y. Yarom, and R. Strackx, \u201cForeshadow: Extracting the keys to the Intel SGX kingdom with transient out-of-order execution,\u201d in Proceedings of the 27th USENIX Security Symposium, USENIX Association, August 2018."},{"key":"e_1_3_2_1_71_1","volume-title":"Technical report","author":"Weisse O.","year":"2018","unstructured":"O. Weisse , J. Van Bulck , M. Minkin , D. Genkin , B. Kasikci , F. Piessens , M. Silberstein , R. Strackx , T. F. Wenisch , and Y. Yarom , \u201c Foreshadow-NG: Breaking the virtual memory abstraction with transient out-of-order execution ,\u201d Technical report , 2018 . O. Weisse, J. Van Bulck, M. Minkin, D. Genkin, B. Kasikci, F. Piessens, M. Silberstein, R. Strackx, T. F. Wenisch, and Y. Yarom, \u201cForeshadow-NG: Breaking the virtual memory abstraction with transient out-of-order execution,\u201d Technical report, 2018."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/1752046.1752047"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132769"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295115"},{"key":"e_1_3_2_1_75_1","first-page":"1651","volume-title":"Proceedings of the 27th USENIX Conference on Security Symposium, SEC'18","author":"Juvekar C.","year":"2018","unstructured":"C. Juvekar , V. Vaikuntanathan , and A. Chandrakasan , \u201c Gazelle: A low latency framework for secure neural network inference ,\u201d in Proceedings of the 27th USENIX Conference on Security Symposium, SEC'18 , ( Berkeley, CA, USA) , pp. 1651 -- 1668 , USENIX Association, 2018 . C. Juvekar, V. Vaikuntanathan, and A. Chandrakasan, \u201cGazelle: A low latency framework for secure neural network inference,\u201d in Proceedings of the 27th USENIX Conference on Security Symposium, SEC'18, (Berkeley, CA, USA), pp. 1651--1668, USENIX Association, 2018."},{"key":"e_1_3_2_1_76_1","first-page":"35","article-title":"Privacy-preserving classification on deep neural network","volume":"2017","author":"Chabanne H.","year":"2017","unstructured":"H. Chabanne , A. de Wargny , J. Milgram , C. Morel , and E. Prouff , \u201c Privacy-preserving classification on deep neural network ,\u201d IACR Cryptology ePrint Archive , vol. 2017 , p. 35 , 2017 . H. Chabanne, A. de Wargny, J. Milgram, C. Morel, and E. Prouff, \u201cPrivacy-preserving classification on deep neural network,\u201d IACR Cryptology ePrint Archive, vol. 2017, p. 35, 2017.","journal-title":"IACR Cryptology ePrint Archive"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.12"}],"event":{"name":"ASPLOS '20: Architectural Support for Programming Languages and Operating Systems","location":"Lausanne Switzerland","acronym":"ASPLOS '20","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGOPS ACM Special Interest Group on Operating Systems","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3373376.3378522","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3373376.3378522","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3373376.3378522","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3373376.3378522","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:38:16Z","timestamp":1750199896000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3373376.3378522"}},"subtitle":["Learning Noise Distributions to Protect Inference Privacy"],"short-title":[],"issued":{"date-parts":[[2020,3,9]]},"references-count":76,"alternative-id":["10.1145\/3373376.3378522","10.1145\/3373376"],"URL":"https:\/\/doi.org\/10.1145\/3373376.3378522","relation":{},"subject":[],"published":{"date-parts":[[2020,3,9]]},"assertion":[{"value":"2020-03-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}