{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T06:06:52Z","timestamp":1767766012899,"version":"3.48.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62306093"],"award-info":[{"award-number":["62306093"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tcad.2025.3576320","type":"journal-article","created":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T13:56:48Z","timestamp":1749045408000},"page":"506-518","source":"Crossref","is-referenced-by-count":0,"title":["SPLAT: Revisiting Latency Attack on Dynamic Neural Networks"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9122-5923","authenticated-orcid":false,"given":"Yu","family":"Li","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"given":"Biao","family":"Huang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1782-1205","authenticated-orcid":false,"given":"Jinyin","family":"Hu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2610-7522","authenticated-orcid":false,"given":"Cheng","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2022.103718"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC.2017.8226047"},{"key":"ref3","article-title":"ExT5: Towards extreme multi-task scaling for transfer learning","author":"Aribandi","year":"2022","journal-title":"arXiv:2111.10952"},{"key":"ref4","first-page":"1","article-title":"Segment anything in high quality","volume-title":"Proc. 37th Adv. Neural Inf. Process. Syst.","author":"Ke"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59710-8_38"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6697"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3131550"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2957724"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435937"},{"key":"ref10","article-title":"Mixture-of-depths: Dynamically allocating compute in transformer-based language models","author":"Raposo","year":"2024","journal-title":"arXiv:2404.02258"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_20"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref14","first-page":"11960","article-title":"Not all images are worth 16x16 words: Dynamic transformers for efficient image recognition","volume-title":"Proc. 35th Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00144"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263619"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP51992.2021.00024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.3013077"},{"key":"ref19","first-page":"1","article-title":"A panda? No, it\u2019s a sloth: Slowdown attacks on adaptive multi-exit neural network inference","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hong"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510088"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM48099.2022.10001235"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01427"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3527155"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3587095"},{"key":"ref25","first-page":"3301","article-title":"Shallow-deep networks: Understanding and mitigating network overthinking","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Kaya"},{"key":"ref26","article-title":"Multi-scale dense networks for resource efficient image classification","author":"Huang","year":"2018","journal-title":"arXiv:1703.09844"},{"key":"ref27","first-page":"1","article-title":"Towards anytime classification in early-exit architectures by enforcing conditional monotonicity","volume-title":"Proc. 37th Adv. Neural Inf. Process. Syst.","author":"Jazbec"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP55844.2023.10285956"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3344120"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2023.08.190"},{"key":"ref31","article-title":"Accelerated inference and reduced forgetting: The dual benefits of early-exit networks in continual learning","author":"Szatkowski","year":"2024","journal-title":"arXiv:2403.07404"},{"key":"ref32","article-title":"HILT: Personalized and adaptive privacy-aware early-exit for reinforcement learning in human-in-the-loop systems","author":"Taherisadr","year":"2024","journal-title":"arXiv:2403.05864"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3639856.3639873"},{"key":"ref34","article-title":"Dynamic early exiting predictive coding neural networks","author":"Zniber","year":"2023","journal-title":"arXiv:2309.02022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/DCOSS-IoT58021.2023.00014"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"ref37","first-page":"4677","article-title":"Accelerating inference for pretrained language models by unified multi-perspective early exiting","volume-title":"Proc. 29th Int. Conf. Comput. Linguist.","author":"Kong"},{"key":"ref38","first-page":"17456","article-title":"Confident adaptive language modeling","volume-title":"Proc. 36th Adv. Neural Inf. Process. Syst.","author":"Schuster"},{"key":"ref39","article-title":"Accelerating LLM inference by enabling intermediate layer decoding","author":"Varshney","year":"2023","journal-title":"arXiv:2310.18581"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/566"},{"key":"ref41","first-page":"18330","article-title":"BERT loses patience: Fast and robust inference with early exit","volume-title":"Proc. 34th Adv. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-8"},{"key":"ref43","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2015","journal-title":"arXiv:1412.6572"},{"key":"ref44","article-title":"Adversarial machine learning at scale","author":"Kurakin","year":"2017","journal-title":"arXiv:1611.01236"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref46","first-page":"1","article-title":"Delving into transferable adversarial examples and black-box attacks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref47","article-title":"Transferability in machine learning: From phenomena to black-box attacks using adversarial samples","author":"Papernot","year":"2016","journal-title":"arXiv:1605.07277"},{"key":"ref48","first-page":"2137","article-title":"Black-box adversarial attacks with limited queries and information","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ilyas"},{"article-title":"Query-efficient hard-label black-box attack: An optimization-based approach","volume-title":"Proc. Int. Conf. Learn. Represent","author":"Cheng","key":"ref49"},{"key":"ref50","first-page":"1","article-title":"Rethinking model ensemble in transfer-based adversarial attacks","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref51","first-page":"1","article-title":"Sign-OPT: A query-efficient hard-label adversarial attack","volume-title":"Proc. 8th Int. Conf. Learn. Represent. (ICLR)","author":"Cheng"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3370849"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00163"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140448"},{"key":"ref55","article-title":"Simple black-box adversarial attacks","author":"Guo","year":"2019","journal-title":"arXiv:1905.07121"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26139"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28156"},{"key":"ref59","article-title":"Delving into transferable adversarial examples and black-box attacks","author":"Liu","year":"2017","journal-title":"arXiv:1611.02770"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3691625"},{"key":"ref61","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"arXiv:1409.1556"},{"key":"ref62","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","journal-title":"arXiv:1512.03385"},{"key":"ref63","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"volume-title":"The CIFAR-10 dataset","year":"2025","author":"Krizhevsky","key":"ref64"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref66","first-page":"2261","article-title":"Densely connected convolutional networks","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Huang"},{"key":"ref67","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Szegedy"},{"key":"ref68","first-page":"1","article-title":"Going deeper with convolutions","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Szegedy"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/43\/11329484\/11023577.pdf?arnumber=11023577","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T05:51:45Z","timestamp":1767765105000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11023577\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":68,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2025.3576320","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"type":"print","value":"0278-0070"},{"type":"electronic","value":"1937-4151"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}