{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:57:32Z","timestamp":1781539052987,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810625","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"2050-2058","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Semantic-Guided Fast Adversarial Training via Class Relationship Exploitation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4709-2892","authenticated-orcid":false,"given":"Yu","family":"Chen","sequence":"first","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2460-7758","authenticated-orcid":false,"given":"Ke","family":"Wang","sequence":"additional","affiliation":[{"name":"Jinan University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0203-2558","authenticated-orcid":false,"given":"Fan","family":"Yang","sequence":"additional","affiliation":[{"name":"Guangdong Institute of Smart Education, Jinan University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0160-7872","authenticated-orcid":false,"given":"Qiang","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6963-4984","authenticated-orcid":false,"given":"Jinwei","family":"Chi","sequence":"additional","affiliation":[{"name":"Guangdong Institute of Smart Education, Jinan University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6296-1419","authenticated-orcid":false,"given":"Honghao","family":"Wei","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Jinan University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","volume-title":"Advances in Neural Information Processing Systems","author":"Alayrac Jean-Baptiste","year":"2019","unstructured":"Jean-Baptiste Alayrac, Jonathan Uesato, Po-Sen Huang, Alhussein Fawzi, Robert Stanforth, and Pushmeet Kohli. 2019. Are Labels Required for Improving Adversarial Robustness?. In Advances in Neural Information Processing Systems , Vol.\u00a032. https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/bea6cfd50b4f5e3c735a972cf0eb8450-Paper.pdf"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_29"},{"key":"e_1_3_3_1_4_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Andriushchenko Maksym","year":"2020","unstructured":"Maksym Andriushchenko and Nicolas Flammarion. 2020. Understanding and improving fast adversarial training. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"e_1_3_3_1_6_2","first-page":"11192","volume-title":"Advances in Neural Information Processing Systems","author":"Carmon Yair","year":"2019","unstructured":"Yair Carmon, Aditi Raghunathan, Ludwig Schmidt, John\u00a0C Duchi, and Percy\u00a0S Liang. 2019. Unlabeled Data Improves Adversarial Robustness. In Advances in Neural Information Processing Systems , Vol.\u00a032. 11192\u201311203. https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/32e0bd1497aa43e02a42f47d9d6515ad-Paper.pdf"},{"key":"e_1_3_3_1_7_2","first-page":"2196","volume-title":"International conference on machine learning","author":"Croce Francesco","year":"2020","unstructured":"Francesco Croce and Matthias Hein. 2020. Minimally distorted adversarial examples with a fast adaptive boundary attack. In International conference on machine learning. PMLR, 2196\u20132205."},{"key":"e_1_3_3_1_8_2","volume-title":"International Conference on Machine Learning (ICML)","author":"Croce Francesco","year":"2020","unstructured":"Francesco Croce and Matthias Hein. 2020. Reliable evaluation of adversarial robustness with an ensemble of diverse attacks. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_3_1_9_2","volume-title":"ICML","author":"Croce Francesco","year":"2020","unstructured":"Francesco Croce and Matthias Hein. 2020. Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. In ICML. arxiv:https:\/\/arXiv.org\/abs\/2003.01690\u00a0[cs.LG]"},{"key":"e_1_3_3_1_10_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"De\u00a0Almeida Felipe","year":"2021","unstructured":"Felipe De\u00a0Almeida, Josu Brea, Guilherme Cazenavette, Nima Alipourfard, Kaan Kosta, Vivek Balasubramanian, and Ping-Yeh Chen. 2021. Robustness via adversarial learning on the fast track. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Pau de Jorge\u00a0Aranda Adel Bibi Riccardo Volpi Amartya Sanyal Philip Torr Gr\u00e9gory Rogez and Puneet Dokania. 2022. Make some noise: Reliable and efficient single-step adversarial training. Advances in Neural Information Processing Systems 35 (2022) 12881\u201312893.","DOI":"10.52202\/068431-0936"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"e_1_3_3_1_13_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Goodfellow Ian\u00a0J","year":"2015","unstructured":"Ian\u00a0J Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and harnessing adversarial examples. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_1_14_2","unstructured":"Sven Gowal Chongli Qin Jonathan Uesato Timothy Mann and Pushmeet Kohli. 2020. Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples. arXiv preprint 2010.03593 (2020). arxiv:https:\/\/arXiv.org\/abs\/2010.03593\u00a0[stat.ML]"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_33"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16989"},{"key":"e_1_3_3_1_19_2","unstructured":"Alex Krizhevsky Geoffrey Hinton et\u00a0al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_3_1_20_2","unstructured":"Yann Le and Xuan Yang. 2015. Tiny imagenet visual recognition challenge. CS 231N 7 7 (2015) 3."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Runqi Lin Chaojian Yu and Tongliang Liu. 2023. Eliminating catastrophic overfitting via abnormal adversarial examples regularization. Advances in Neural Information Processing Systems 36 (2023) 67866\u201367885.","DOI":"10.52202\/075280-2968"},{"key":"e_1_3_3_1_22_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Madry Aleksander","year":"2018","unstructured":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Alexandru Vladu. 2018. Towards deep learning models resistant to adversarial attacks. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30147"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00287"},{"key":"e_1_3_3_1_26_2","volume-title":"NeurIPS","author":"Pang Tianyu","year":"2020","unstructured":"Tianyu Pang, Xiao Yang, Yinpeng Dong, Kun Xu, Hang Su, and Jun Zhu. 2020. Boosting Adversarial Training with Hypersphere Embedding. In NeurIPS. arxiv:https:\/\/arXiv.org\/abs\/2002.08619\u00a0[cs.LG]"},{"key":"e_1_3_3_1_27_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Shafahi Ali","year":"2019","unstructured":"Ali Shafahi, Mahyar Taylor, Pavel Izmailov, Mojtaba Ghandar, Ehsan Faghri, David Studer, and Tom Goldstein. 2019. Adversarial training for free!. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_1_28_2","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Shao Jianhui","year":"2021","unstructured":"Jianhui Shao, Guotian Peng, Xuan Li, Yunqi Chen, and Yuqi Zhang. 2021. Robust training with self-paced curriculum. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_3_1_29_2","unstructured":"Gaurang Sriramanan Sravanti Addepalli Arya Baburaj et\u00a0al. 2020. Guided adversarial attack for evaluating and enhancing adversarial defenses. Advances in Neural Information Processing Systems 33 (2020) 20297\u201320308."},{"key":"e_1_3_3_1_30_2","unstructured":"Gaurang Sriramanan Sravanti Addepalli Arya Baburaj et\u00a0al. 2021. Towards efficient and effective adversarial training. Advances in Neural Information Processing Systems 34 (2021) 11821\u201311833."},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28330"},{"key":"e_1_3_3_1_32_2","volume-title":"International Conference on Learning Representations","author":"Wang Yisen","year":"2020","unstructured":"Yisen Wang, Difan Zou, Jinfeng Yi, James Bailey, Xingjun Ma, and Quanquan Gu. 2020. Improving Adversarial Robustness Requires Revisiting Misclassified Examples. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rklOg6EFwS"},{"key":"e_1_3_3_1_33_2","first-page":"144","volume-title":"European Conference on Computer Vision","author":"Wang Zhaoxin","year":"2024","unstructured":"Zhaoxin Wang, Handing Wang, Cong Tian, and Yaochu Jin. 2024. Preventing catastrophic overfitting in fast adversarial training: A bi-level optimization perspective. In European Conference on Computer Vision. Springer, 144\u2013160."},{"key":"e_1_3_3_1_34_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Wong Eric","year":"2020","unstructured":"Eric Wong, Leslie Rice, and Zico Kolter. 2020. Fast is better than free: Revisiting adversarial training. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_1_35_2","unstructured":"Boxi Wu Jinghui Chen Deng Cai Xiaofei He and Quanquan Gu. 2020. Does Network Width Really Help Adversarial Robustness?arXiv 2010.01279 (2020). arxiv:https:\/\/arXiv.org\/abs\/2010.01279\u00a0[cs.LG]"},{"key":"e_1_3_3_1_36_2","volume-title":"NeurIPS","author":"Wu Dongxian","year":"2020","unstructured":"Dongxian Wu, Shu tao Xia, and Yisen Wang. 2020. Adversarial Weight Perturbation Helps Robust Generalization. In NeurIPS."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/543"},{"key":"e_1_3_3_1_38_2","volume-title":"ICML","author":"Zhang Hongyang","unstructured":"Hongyang Zhang, Yaodong Yu, Jiantao Jiao, Eric Xing, Laurent\u00a0El Ghaoui, and Michael Jordan. [n. d.]. Theoretically Principled Trade-off between Robustness and Accuracy. In ICML. http:\/\/proceedings.mlr.press\/v97\/zhang19p.html"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00126"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:41:44Z","timestamp":1781538104000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810625"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":38,"alternative-id":["10.1145\/3805622.3810625","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810625","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}