{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T17:05:58Z","timestamp":1772643958056,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T00:00:00Z","timestamp":1743292800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,30]]},"DOI":"10.1145\/3721146.3721948","type":"proceedings-article","created":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T17:42:05Z","timestamp":1743529325000},"page":"31-38","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Exploiting Unstructured Sparsity in Fully Homomorphic Encrypted DNNs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5673-9911","authenticated-orcid":false,"given":"Aidan","family":"Ferguson","sequence":"first","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-0698","authenticated-orcid":false,"given":"Perry","family":"Gibson","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2030-5000","authenticated-orcid":false,"given":"Lara","family":"D'Agata","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6988-0266","authenticated-orcid":false,"given":"Parker","family":"McLeod","sequence":"additional","affiliation":[{"name":"AMD, Folsom, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5391-7248","authenticated-orcid":false,"given":"Ferhat","family":"Yaman","sequence":"additional","affiliation":[{"name":"AMD, Boston, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4339-4049","authenticated-orcid":false,"given":"Amitabh","family":"Das","sequence":"additional","affiliation":[{"name":"AMD, Austin, Texas, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1669-5519","authenticated-orcid":false,"given":"Ian","family":"Colbert","sequence":"additional","affiliation":[{"name":"AMD, San Diego, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2243-389X","authenticated-orcid":false,"given":"Jos\u00e9","family":"Cano","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,4]]},"reference":[{"key":"e_1_3_2_1_2_1","volume-title":"General functional bootstrapping using CKKS. Cryptology ePrint Archive","author":"Alexandru Andreea","year":"2024","unstructured":"Andreea Alexandru, Andrey Kim, and Yuriy Polyakov. 2024. General functional bootstrapping using CKKS. Cryptology ePrint Archive (2024)."},{"key":"e_1_3_2_1_3_1","unstructured":"Ayoub Benaissa Bilal Retiat Bogdan Cebere and Alaa Eddine Belfedhal. 2021. TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption. arXiv:2104.03152 [cs.CR]"},{"key":"e_1_3_2_1_4_1","volume-title":"International Conference on Machine Learning. PMLR, 2397--2430","author":"Biderman Stella","year":"2023","unstructured":"Stella Biderman, Hailey Schoelkopf, Quentin Gregory Anthony, Herbie Bradley, Kyle O'Brien, Eric Hallahan, Mohammad Aflah Khan, Shivanshu Purohit, USVSN Sai Prashanth, Edward Raff, et al. 2023. Pythia: A suite for analyzing large language models across training and scaling. In International Conference on Machine Learning. PMLR, 2397--2430."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77870-5_21"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2633600"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-22792-9_29"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467210"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/tifs.2014.2363765"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70694-8_15"},{"key":"e_1_3_2_1_11_1","unstructured":"Jamie Cui Chaochao Chen Lingjuan Lyu Carl Yang and Li Wang. 2021. Exploiting Data Sparsity in Secure Cross-Platform Social Recommendation. https:\/\/www.cs.emory.edu\/~jyang71\/files\/s3rec.pdf"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Gianni Franchi Andrei Bursuc Emanuel Aldea S\u00e9verine Dubuisson and Isabelle Bloch. [n. d.]. TRADI: Tracking deep neural network weight distributions. https:\/\/www.ecva.net\/papers\/eccv_2020\/papers_ECCV\/papers\/123620103.pdf","DOI":"10.1007\/978-3-030-58520-4_7"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433723"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1536414.1536440"},{"key":"e_1_3_2_1_15_1","unstructured":"Ga\u00ebl Guennebaud Beno\u00eet Jacob et al. 2010. Eigen v3. http:\/\/eigen.tuxfamily.org."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2022.952709"},{"key":"e_1_3_2_1_17_1","volume-title":"Nicolas Bohm Agostini, and David Kaeli","author":"Haris Jude","year":"2021","unstructured":"Jude Haris, Perry Gibson, Jos\u00e9 Cano, Nicolas Bohm Agostini, and David Kaeli. 2021. SECDA: Efficient Hardware\/Software Co-Design of FPGA-based DNN Accelerators for Edge Inference. In 2021 IEEE 33rd International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)."},{"key":"e_1_3_2_1_18_1","volume-title":"Nicolas Bohm Agostini, and David Kaeli","author":"Haris Jude","year":"2023","unstructured":"Jude Haris, Perry Gibson, Jos\u00e9 Cano, Nicolas Bohm Agostini, and David Kaeli. 2023. SECDA-TFLite: A Toolkit for Efficient Development of FPGA-based DNN Accelerators for Edge Inference. In Journal of Parallel and Distributed Computing."},{"key":"e_1_3_2_1_19_1","volume-title":"Designing Efficient LLM Accelerators for Edge Devices. In Workshop on New Approaches for Addressing the Computing Requirements of LLMs and GNNs (ARC-LG) at ISCA.","author":"Haris Jude","year":"2024","unstructured":"Jude Haris, Rappy Saha, Wenhao Hu, and Jos\u00e9 Cano. 2024. Designing Efficient LLM Accelerators for Edge Devices. In Workshop on New Approaches for Addressing the Computing Requirements of LLMs and GNNs (ARC-LG) at ISCA."},{"key":"e_1_3_2_1_20_1","volume-title":"Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770--778","author":"He Kaiming","year":"2015","unstructured":"Kaiming He, X. Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770--778."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1587\/transfun.E99.A.73","article-title":"Packing messages and optimizing bootstrapping in GSW-FHE","volume":"99","author":"Hiromasa Ryo","year":"2016","unstructured":"Ryo Hiromasa, Masayuki Abe, and Tatsuaki Okamoto. 2016. Packing messages and optimizing bootstrapping in GSW-FHE. IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences 99, 1 (2016), 73--82.","journal-title":"IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences"},{"key":"e_1_3_2_1_22_1","volume-title":"Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures. arXiv:1607.03250 [cs] (Jul","author":"Hu Hengyuan","year":"2016","unstructured":"Hengyuan Hu, Rui Peng, Yu-Wing Tai, and Chi-Keung Tang. 2016. Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures. arXiv:1607.03250 [cs] (Jul 2016). https:\/\/arxiv.org\/abs\/1607.03250"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-022-04850-4"},{"key":"e_1_3_2_1_24_1","unstructured":"Jiachen Jiang Yiqi Zhong and Jinxin Zhou. 2023. The Efficiency Spectrum of Large Language Models: An Algorithmic Survey. https:\/\/arxiv.org\/pdf\/2312.00678"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243837"},{"key":"e_1_3_2_1_26_1","unstructured":"K-miran. 2018. GitHub - K-miran\/HEMat: Homomorphic matrix computation. https:\/\/github.com\/K-miran\/HEMat"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.2172\/7093021"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3287564"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3159694"},{"key":"e_1_3_2_1_30_1","volume-title":"ML with HE: Privacy Preserving Machine Learning Inferences for Genome Studies. arXiv e-prints","author":"Ma\u011fara S","year":"2021","unstructured":"\u015eS Ma\u011fara, C Y\u0131ld\u0131r\u0131m, F Yaman, B Dileko\u011flu, FR Tuta\u015f, E \u00d6zt\u00fcrk, K Kaya, \u00d6 Ta\u015ftan, and E Sava\u015f. 2021. ML with HE: Privacy Preserving Machine Learning Inferences for Genome Studies. arXiv e-prints (2021), arXiv-2110."},{"key":"e_1_3_2_1_31_1","volume-title":"Mundo Oncel, Tuzel Golnoosh, Samei Mohammad, Rastegari Mehrdad, and Farajtabar Apple.","author":"Mirzadeh Iman","year":"2023","unstructured":"Iman Mirzadeh, Keivan Alizadeh, Sachin Mehta, Carlo Del, Mundo Oncel, Tuzel Golnoosh, Samei Mohammad, Rastegari Mehrdad, and Farajtabar Apple. 2023. ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models. https:\/\/arxiv.org\/pdf\/2310.04564"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.3390\/s22218124"},{"key":"e_1_3_2_1_33_1","unstructured":"Reiner Pope Sholto Douglas Aakanksha Chowdhery Jacob Devlin James Bradbury Anselm Levskaya Jonathan Heek Kefan Xiao Shivani Agrawal and Jeff Dean. 2022. Efficiently Scaling Transformer Inference. https:\/\/arxiv.org\/abs\/2211.05102"},{"key":"e_1_3_2_1_34_1","unstructured":"PyTorch. [n. d.]. torch.nn.init --- PyTorch 2.2 documentation. https:\/\/pytorch.org\/docs\/stable\/nn.init.html"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3267323.3268952"},{"key":"e_1_3_2_1_36_1","volume-title":"Iterative Methods for Sparse Linear Systems","author":"Saad Yousef","unstructured":"Yousef Saad. 2003. Iterative Methods for Sparse Linear Systems Second Edition Yousef Saad. https:\/\/www-users.cse.umn.edu\/~saad\/IterMethBook_2ndEd.pdf"},{"key":"e_1_3_2_1_37_1","volume-title":"https:\/\/github.com\/Microsoft\/SEAL. Microsoft Research","author":"SEAL","unstructured":"SEAL 2023. Microsoft SEAL (release 4.1). https:\/\/github.com\/Microsoft\/SEAL. Microsoft Research, Redmond, WA."},{"key":"e_1_3_2_1_38_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations.","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_39_1","unstructured":"snucrypto. 2023. HEAAN. https:\/\/github.com\/snucrypto\/HEAAN. https:\/\/github.com\/snucrypto\/HEAAN"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2024.3363900"}],"event":{"name":"EuroMLSys '25: 5th Workshop on Machine Learning and Systems","location":"World Trade Center Rotterdam Netherlands","acronym":"EuroMLSys '25","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 5th Workshop on Machine Learning and Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721146.3721948","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721146.3721948","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:57:39Z","timestamp":1750298259000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721146.3721948"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,30]]},"references-count":39,"alternative-id":["10.1145\/3721146.3721948","10.1145\/3721146"],"URL":"https:\/\/doi.org\/10.1145\/3721146.3721948","relation":{},"subject":[],"published":{"date-parts":[[2025,3,30]]},"assertion":[{"value":"2025-04-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}