{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T20:09:35Z","timestamp":1778789375189,"version":"3.51.4"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62002167"],"award-info":[{"award-number":["62002167"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072239"],"award-info":[{"award-number":["62072239"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122023"],"award-info":[{"award-number":["62122023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of JiangSu Province","award":["BK20200461"],"award-info":[{"award-number":["BK20200461"]}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2021J01544"],"award-info":[{"award-number":["2021J01544"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Dependable and Secure Comput."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tdsc.2023.3271956","type":"journal-article","created":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T18:56:18Z","timestamp":1682967378000},"page":"1155-1172","source":"Crossref","is-referenced-by-count":19,"title":["Quantization Backdoors to Deep Learning Commercial Frameworks"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9069-7731","authenticated-orcid":false,"given":"Hua","family":"Ma","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering, The University of Adelaide, Adelaide, SA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5385-9414","authenticated-orcid":false,"given":"Huming","family":"Qiu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5783-2172","authenticated-orcid":false,"given":"Yansong","family":"Gao","sequence":"additional","affiliation":[{"name":"Data61, CSIRO, Eveleigh, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3604-5369","authenticated-orcid":false,"given":"Zhi","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Western Australia, Perth, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9695-7947","authenticated-orcid":false,"given":"Alsharif","family":"Abuadbba","sequence":"additional","affiliation":[{"name":"Data61, CSIRO, Eveleigh, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9172-4252","authenticated-orcid":false,"given":"Minhui","family":"Xue","sequence":"additional","affiliation":[{"name":"Data61, CSIRO, Eveleigh, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1632-5737","authenticated-orcid":false,"given":"Anmin","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8712-2964","authenticated-orcid":false,"given":"Jiliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Semiconductors (College of Integrated Circuits, Hunan University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3242-8197","authenticated-orcid":false,"given":"Said F.","family":"Al-Sarawi","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, The University of Adelaide, Adelaide, SA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0945-2674","authenticated-orcid":false,"given":"Derek","family":"Abbott","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, The University of Adelaide, Adelaide, SA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"TinyML: Machine Learning With Tensorflow Lite on Arduino and Ultra-Low-Power Microcontrollers","author":"Warden","year":"2019"},{"key":"ref2","volume-title":"Machine Learning Projects for Mobile Applications: Build Android and IOS Applications Using TensorFlow Lite and Core ML","author":"Karthikeyan","year":"2018"},{"key":"ref3","article-title":"Why TinyML is a giant opportunity","author":"Machine","year":"2021"},{"key":"ref4","article-title":"TensorFlow lite micro: Embedded machine learning on TinyML systems","author":"David","year":"2020"},{"key":"ref5","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume-title":"Proc. 12th USENIX Symp. Operating Syst. Des. Implementation","author":"Abadi"},{"key":"ref6","article-title":"TensorFlow lite: ML for mobile and IoT devices (TF dev summit \u201920)","author":"Davis","year":"2021"},{"key":"ref7","article-title":"PyTorch mobile: End-to-end workflow from training to deployment for iOS and Android mobile devices","year":"2021"},{"key":"ref8","article-title":"Post-training quantization","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3423338"},{"key":"ref10","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00031"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3359789.3359790"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3363216"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00034"},{"key":"ref15","first-page":"4107","article-title":"Binarized neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hubara"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref17","article-title":"XNOR-Net++: Improved binary neural networks","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Bulat"},{"key":"ref18","article-title":"Training binary neural networks with real-to-binary convolutions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Martinez"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2682138"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2857019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107281"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tcad.2022.3197499"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3431920.3439296"},{"key":"ref25","first-page":"10271","article-title":"Pushing the limits of narrow precision inferencing at cloud scale with microsoft floating point","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Darvish Rouhani"},{"key":"ref26","first-page":"7197","article-title":"Up or down? Adaptive rounding for post-training quantization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nagel"},{"key":"ref27","first-page":"4466","article-title":"Accurate post training quantization with small calibration sets","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hubara"},{"issue":"9","key":"ref28","article-title":"Tensorflow lite: On-device machine learning framework","volume":"57","author":"Shuangfeng","year":"2020","journal-title":"J. Comput. Res. Develop."},{"key":"ref29","article-title":"Backdoor attacks and countermeasures on deep learning: A comprehensive review","author":"Gao","year":"2020"},{"key":"ref30","article-title":"BadNets: Identifying vulnerabilities in the machine learning model supply chain","author":"Gu","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243757"},{"key":"ref32","article-title":"Poison frogs! targeted clean-label poisoning attacks on neural networks","author":"Shafahi","year":"2018"},{"key":"ref33","first-page":"2938","article-title":"How to backdoor federated learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Bagdasaryan"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/647"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3427228.3427264"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tdsc.2021.3055844"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417231"},{"key":"ref38","first-page":"1615","article-title":"Turning your weakness into a strength: Watermarking deep neural networks by backdooring","volume-title":"Proc. 27th USENIX Secur. Symp.","author":"Adi"},{"key":"ref39","article-title":"Entangled watermarks as a defense against model extraction","volume-title":"Proc. 30th USENIX Secur. Symp.","author":"Jia"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP53844.2022.00048"},{"key":"ref41","first-page":"443","article-title":"Seeing is not believing: Camouflage attacks on image scaling algorithms","volume-title":"Proc. 28th USENIX Secur. Symp.","author":"Xiao"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/SPW50608.2020.00024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3354209"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6871"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3160359"},{"key":"ref46","first-page":"9303","article-title":"Qu-anti-zation: Exploiting quantization artifacts for achieving adversarial outcomes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hong"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3485832.3485881"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_41"},{"key":"ref49","article-title":"Targeted backdoor attacks on deep learning systems using data poisoning","author":"Chen","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2018.23291"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412130"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref54","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.016"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref57","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref58","article-title":"Demon in the variant: Statistical analysis of DNNs for robust backdoor contamination detection","volume-title":"Proc. 30th USENIX Secur. Symp.","author":"Tang"},{"key":"ref59","article-title":"Tabor: A highly accurate approach to inspecting and restoring trojan backdoors in AI systems","author":"Guo","year":"2019"},{"key":"ref60","article-title":"Representative dataset","year":"2021"},{"key":"ref61","first-page":"175","article-title":"Bypassing backdoor detection algorithms in deep learning","volume-title":"Proc. IEEE Eur. Symp. Secur. Privacy","author":"Shokri"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/tifs.2023.3324318"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00470-5_13"},{"key":"ref64","article-title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833688"}],"container-title":["IEEE Transactions on Dependable and Secure Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8858\/10530496\/10113762.pdf?arnumber=10113762","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,24]],"date-time":"2024-05-24T04:52:32Z","timestamp":1716526352000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10113762\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":65,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tdsc.2023.3271956","relation":{},"ISSN":["1545-5971","1941-0018","2160-9209"],"issn-type":[{"value":"1545-5971","type":"print"},{"value":"1941-0018","type":"electronic"},{"value":"2160-9209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}