{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T14:56:11Z","timestamp":1781794571335,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62272459"],"award-info":[{"award-number":["62272459"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,22]]},"DOI":"10.1145\/3787109.3815251","type":"proceedings-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T14:17:19Z","timestamp":1781792239000},"page":"750-757","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AegisX: An Acceleration Framework for Moving Target Defenses to Boost Adversarial Robustness and Computational Efficiency"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1432-6429","authenticated-orcid":false,"given":"Xingbin","family":"Wang","sequence":"first","affiliation":[{"name":"School Of CyberSecurity, Tianjin University, Tianjin, Tianjin, China and State Key Laboratory of Cyberspace Security Defense, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6318-6769","authenticated-orcid":false,"given":"Kang","family":"Li","sequence":"additional","affiliation":[{"name":"School Of CyberSecurity, Tianjin University, Tianjin, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8994-7747","authenticated-orcid":false,"given":"Mingyang","family":"Zhao","sequence":"additional","affiliation":[{"name":"School Of CyberSecurity, Tianjing University, Tianjin, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6951-5662","authenticated-orcid":false,"given":"Chaochao","family":"Zhang","sequence":"additional","affiliation":[{"name":"NingboTech University, Ningbo, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2125-4336","authenticated-orcid":false,"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hubei University of Arts and Science, Xiangyang, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9215-7632","authenticated-orcid":false,"given":"Rui","family":"Hou","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474370.3485659"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485832.3485899"},{"key":"e_1_3_3_1_4_2","first-page":"274","volume-title":"International conference on machine learning","author":"Athalye Anish","year":"2018","unstructured":"Anish Athalye, Nicholas Carlini, and David Wagner. 2018. Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples. In International conference on machine learning. PMLR, 274\u2013283."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00081"},{"key":"e_1_3_3_1_6_2","unstructured":"Bocheng Chen Hanqing Guo and Qiben Yan. 2024. FlexLLM: Exploring LLM customization for moving target defense on black-box LLMs against jailbreak attacks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.07672 (2024)."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3605760.3623764"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037700"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Yexiang Chen Subhash Lakshminarayana and H\u00a0Vincent Poor. 2025. Moving target defense against adversarial false data injection attacks in power grids. IEEE Internet of Things Journal (2025).","DOI":"10.1109\/JIOT.2025.3560127"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00027"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480082"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00031"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00062"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Lucas Gnecco\u00a0Heredia Muni\u00a0Sreenivas Pydi Laurent Meunier Benjamin Negrevergne and Yann Chevaleyre. 2023. On the role of randomization in adversarially robust classification. Advances in Neural Information Processing Systems 36 (2023) 79293\u201379319.","DOI":"10.52202\/075280-3471"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621413"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Oscar\u00a0H Ibarra and Chul\u00a0E Kim. 1977. Heuristic algorithms for scheduling independent tasks on nonidentical processors. Journal of the ACM (JACM) 24 2 (1977) 280\u2013289.","DOI":"10.1145\/322003.322011"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358252"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00016"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCTCS58815.2023.00115"},{"key":"e_1_3_3_1_20_2","unstructured":"Xingjun Ma Yifeng Gao Yixu Wang Ruofan Wang Xin Wang Ye Sun Yifan Ding Hengyuan Xu Yunhao Chen Yunhan Zhao et\u00a0al. [n. d.]. Safety at Scale: A Comprehensive Survey of Large Model Safety 2025. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.05206 ([n. d.])."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Yuhao Mao Mark M\u00fcller Marc Fischer and Martin Vechev. 2023. Connecting certified and adversarial training. Advances in Neural Information Processing Systems 36 (2023) 73422\u201373440.","DOI":"10.52202\/075280-3211"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM52596.2021.9652915"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.30"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Samuel Panterino and Matthew Fellington. 2024. Dynamic moving target defense for mitigating targeted llm prompt injection. Authorea Preprints (2024).","DOI":"10.36227\/techrxiv.171822345.56781952\/v1"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/SAHCN.2004.1381916"},{"key":"e_1_3_3_1_26_2","first-page":"7717","volume-title":"International Conference on Machine Learning","author":"Pinot Rafael","year":"2020","unstructured":"Rafael Pinot, Raphael Ettedgui, Geovani Rizk, Yann Chevaleyre, and Jamal Atif. 2020. Randomization matters how to defend against strong adversarial attacks. In International Conference on Machine Learning. PMLR, 7717\u20137727."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Rafael Pinot Laurent Meunier Florian Yger C\u00e9dric Gouy-Pailler Yann Chevaleyre and Jamal Atif. 2022. On the robustness of randomized classifiers to adversarial examples. Machine Learning 111 9 (2022) 3425\u20133457.","DOI":"10.1007\/s10994-022-06216-6"},{"key":"e_1_3_3_1_28_2","unstructured":"Y Qian Q Shao J Wang X Lin Y Guo Z Gu B Wang and C Wu. [n. d.]. EI-MTD: Moving Target Defense for Edge Intelligence against Adversarial Attacks. arXiv 2020. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2009.10537 ([n. d.])."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS48437.2020.00016"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3356250.3360025"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378532"},{"key":"e_1_3_3_1_32_2","unstructured":"Huanrui Yang Jingyang Zhang Hongliang Dong Nathan Inkawhich Andrew Gardner Andrew Touchet Wesley Wilkes Heath Berry and Hai Li. 2020. Dverge: diversifying vulnerabilities for enhanced robust generation of ensembles. Advances in Neural Information Processing Systems 33 (2020) 5505\u20135515."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Tao Zhang Fanyu Kong Dongshang Deng Xiangyun Tang Xuangou Wu Changqiao Xu Liehuang Zhu Jiqiang Liu Bo Ai Zhu Han et\u00a0al. 2025. Moving target defense meets artificial-intelligence-driven network: A comprehensive survey. IEEE Internet of Things Journal 12 10 (2025) 13384\u201313397.","DOI":"10.1109\/JIOT.2025.3533016"}],"event":{"name":"GLSVLSI '26: Great Lakes Symposium on VLSI 2026","location":"Canandaigua , NY , USA","acronym":"GLSVLSI '26","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CEDA"]},"container-title":["Proceedings of the Great Lakes Symposium on VLSI 2026"],"original-title":[],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T14:36:34Z","timestamp":1781793394000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3787109.3815251"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":32,"alternative-id":["10.1145\/3787109.3815251","10.1145\/3787109"],"URL":"https:\/\/doi.org\/10.1145\/3787109.3815251","relation":{},"subject":[],"published":{"date-parts":[[2026,6,22]]},"assertion":[{"value":"2026-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}