{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T19:26:27Z","timestamp":1784402787217,"version":"3.55.0"},"reference-count":121,"publisher":"Association for Computing Machinery (ACM)","issue":"10","license":[{"start":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T00:00:00Z","timestamp":1746576000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"DoD\/U.S. Army Research Laboratory at Howard University","award":["W911NF-20-2-0277"],"award-info":[{"award-number":["W911NF-20-2-0277"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2025,10,31]]},"abstract":"<jats:p>The emergence of Vision Transformers (ViTs) has marked a significant advancement in machine learning, particularly in applications requiring robust visual recognition capabilities, such as traffic sign detection for autonomous driving systems. But, deploying these models in adversarial environments where robustness is critical remains a challenge. This survey provides a comprehensive review of the integration of ViTs in traffic sign detection and recognition, emphasizing their vulnerability to adversarial attacks and the methods developed to enhance their robustness. This article also presents a compressive comparison of ViTs in a tabular form for side-by-side comparison.<\/jats:p>","DOI":"10.1145\/3729167","type":"journal-article","created":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T11:19:06Z","timestamp":1744283946000},"page":"1-33","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Recent Advances in Vision Transformer Robustness Against Adversarial Attacks in Traffic Sign Detection and Recognition: A Survey"],"prefix":"10.1145","volume":"57","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2719-8611","authenticated-orcid":false,"given":"Oluwajuwon","family":"Fawole","sequence":"first","affiliation":[{"name":"DoD Center of Excellence in AI\/ML and Department of Electrical Engineering &amp; Computer Science, Howard University, Washington, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3638-3464","authenticated-orcid":false,"given":"Danda","family":"Rawat","sequence":"additional","affiliation":[{"name":"DoD Center of Excellence in AI\/ML and Department of Electrical Engineering &amp; Computer Science, Howard University, Washington, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,5,7]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2807385"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3127960"},{"issue":"5","key":"e_1_3_1_4_2","first-page":"272","article-title":"Random forests and decision trees","volume":"9","author":"Ali Jehad","year":"2012","unstructured":"Jehad Ali, Rehanullah Khan, Nasir Ahmad, and Imran Maqsood. 2012. Random forests and decision trees. International Journal of Computer Science Issues (IJCSI) 9, 5 (2012), 272.","journal-title":"International Journal of Computer Science Issues (IJCSI)"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00346"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCAI58221.2023.10199560"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/11744023_32"},{"key":"e_1_3_1_8_2","unstructured":"Kshitij Bhardwaj. 2024. PQV-Mobile: A combined pruning and quantization toolkit to optimize vision transformers for mobile applications. In Proceedings of the Workshop on Efficient Systems for Foundation Models II at ICML 2024. Available at: https:\/\/openreview.net\/forum?id=RGkJmq5gIJ"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01007"},{"key":"e_1_3_1_10_2","unstructured":"Wieland Brendel Jonas Rauber and Matthias Bethge. 2018. Decision-based adversarial attacks: Reliable attacks against black-box machine learning models. In Proceedings of the International Conference on Learning Representations (ICLR 2018). Available at: https:\/\/openreview.net\/forum?id=SyZI0GWCZ"},{"key":"e_1_3_1_11_2","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops","author":"Brickwedde Fabian","year":"2018","unstructured":"Fabian Brickwedde, Steffen Abraham, and Rudolf Mester. 2018. Exploiting single image depth prediction for mono-stixel estimation. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops."},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2908062"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140448"},{"key":"e_1_3_1_16_2","article-title":"A semi-supervised learning framework combining CNN and multi-scale transformer for traffic sign detection and recognition","author":"Chen Siyun","year":"2024","unstructured":"Siyun Chen, Zhenxin Zhang, Liqiang Zhang, Rixing He, Zhen Li, Mengbing Xu, and Hao Ma. 2024. A semi-supervised learning framework combining CNN and multi-scale transformer for traffic sign detection and recognition. IEEE Internet of Things Journal 11, 11 (2024), 19500\u201319519.","journal-title":"IEEE Internet of Things Journal"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3395118"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.5555\/648054.743935"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","unstructured":"Anxhelo Diko Danilo Avola Marco Cascio and Luigi Cinque. 2024. ReViT: Enhancing vision transformers feature diversity with attention residual connections. Pattern Recognition 156 (2024) 110853. 10.1016\/j.patcog.2024.110853","DOI":"10.1016\/j.patcog.2024.110853"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071047"},{"key":"e_1_3_1_22_2","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. An image is worth 16\u00d716 words: transformers for image recognition at scale. In Proceedings of the International Conference on Learning Representations (ICLR 2021). Available at: https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_1_23_2","first-page":"1","volume-title":"Proceedings of the Conference on Robot Learning","author":"Dosovitskiy Alexey","year":"2017","unstructured":"Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, and Vladlen Koltun. 2017. CARLA: An open urban driving simulator. In Proceedings of the Conference on Robot Learning. PMLR, 1\u201316."},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_5"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00175"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCKE60553.2023.10326288"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.3390\/math10152733"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2795041"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TE.2013.2239997"},{"key":"e_1_3_1_30_2","unstructured":"Ian J. Goodfellow Jonathon Shlens and Christian Szegedy. 2015. Explaining and harnessing adversarial examples. In Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015). San Diego CA USA. Available at: http:\/\/arxiv.org\/abs\/1412.6572"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3593042"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2012.2208909"},{"key":"e_1_3_1_33_2","first-page":"1","article-title":"Addressing ethical challenges in automated vehicles: Bridging the gap with hybrid AI and augmented utilitarianism","author":"Gros Chloe","year":"2024","unstructured":"Chloe Gros, Leon Kester, Marieke Martens, and Peter Werkhoven. 2024. Addressing ethical challenges in automated vehicles: Bridging the gap with hybrid AI and augmented utilitarianism. AI and Ethics (2024), 1\u201314.","journal-title":"AI and Ethics"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.1888"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_24"},{"key":"e_1_3_1_36_2","article-title":"Physical adversarial attacks for camera-based smart systems: Current trends, categorization, applications, research challenges, and future outlook","author":"Shafique Amira Guesmi, Muhammad Abdullah Hanif, Bassem Ouni, and Muhammad","year":"2023","unstructured":"Amira Guesmi, Muhammad Abdullah Hanif, Bassem Ouni, and Muhammad Shafique . 2023. Physical adversarial attacks for camera-based smart systems: Current trends, categorization, applications, research challenges, and future outlook. IEEE Access 11 (2023), 109617\u2013109668.","journal-title":"IEEE Access"},{"key":"e_1_3_1_37_2","unstructured":"Fu-Ming Guo and Yingfang Fan. 2022. Zero-shot and few-shot learning for lung cancer multi-label classification using vision transformer. arXiv:2205.15290. Retrieved from https:\/\/arxiv.org\/abs\/2205.15290"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00400"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01610"},{"key":"e_1_3_1_40_2","article-title":"Designing robust transformers using robust kernel density estimation","author":"Han Xing","year":"2024","unstructured":"Xing Han, Tongzheng Ren, Tan Nguyen, Khai Nguyen, Joydeep Ghosh, and Nhat Ho. 2024. Designing robust transformers using robust kernel density estimation. In Proceedings of the 37th International Conference on Neural Information Processing Systems.","journal-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2890293"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/5254.708428"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2013.6706807"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","unstructured":"Xixu Hu Runkai Zheng Jindong Wang Cheuk Hang Leung Qi Wu and Xing Xie. 2024. SpecFormer: Guarding vision transformer robustness via maximum singular value penalization. In Computer Vision - ECCV 2024: 18th European Conference Milan Italy September 29 -October 4 2024 Proceedings Part LIV. Springer-Verlag Berlin Heidelberg 345\u2013362. 10.1007\/978-3-031-72949-2_20","DOI":"10.1007\/978-3-031-72949-2_20"},{"issue":"1","key":"e_1_3_1_47_2","first-page":"1","article-title":"Deep learning adversarial attacks and defenses in autonomous vehicles: A systematic literature review from a safety perspective","volume":"58","author":"Ibrahum Ahmed Dawod Mohammed","year":"2025","unstructured":"Ahmed Dawod Mohammed Ibrahum, Manzoor Hussain, and Jang-Eui Hong. 2025. Deep learning adversarial attacks and defenses in autonomous vehicles: A systematic literature review from a safety perspective. Artificial Intelligence Review 58, 1 (2025), 1\u201353.","journal-title":"Artificial Intelligence Review"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","unstructured":"Ryota Iijima Sayaka Shiota and Hitoshi Kiya. 2024. A random ensemble of encrypted vision transformers for adversarially robust defense. IEEE Access 12 (2024) 69206\u201369216. 10.1109\/ACCESS.2024.3400958. arXiv+2.","DOI":"10.1109\/ACCESS.2024.3400958"},{"key":"e_1_3_1_49_2","first-page":"2137","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Ilyas Andrew","year":"2018","unstructured":"Andrew Ilyas, Logan Engstrom, Anish Athalye, and Jessy Lin. 2018. Black-box adversarial attacks with limited queries and information. In Proceedings of the International Conference on Machine Learning. PMLR, 2137\u20132146."},{"key":"e_1_3_1_50_2","unstructured":"Chashi Mahiul Islam Samuel Jacob Chacko Mao Nishino and Xiuwen Liu. 2025. Mechanistic understandings of representation vulnerabilities and engineering robust vision transformers. arXiv:2502.04679. Retrieved from https:\/\/arxiv.org\/abs\/2502.04679"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCKE60553.2023.10326242"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.2478\/ttj-2024-0003"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-28649-3_7"},{"key":"e_1_3_1_54_2","unstructured":"Junae Kim and Amardeep Kaur. 2024. A survey on adversarial robustness of LiDAR-based machine learning perception in autonomous vehicles. arXiv:2411.13778. Retrieved from https:\/\/arxiv.org\/abs\/2411.13778"},{"key":"e_1_3_1_55_2","first-page":"125","article-title":"Exploring ethical considerations in AI-driven autonomous vehicles: Balancing safety and privacy","volume":"2","author":"Kumar A.","year":"2024","unstructured":"A. Kumar. 2024. Exploring ethical considerations in AI-driven autonomous vehicles: Balancing safety and privacy. Journal of Artificial Intelligence General Science (JAIGS) 2, 1 (2024), 125\u2013138.","journal-title":"Journal of Artificial Intelligence General Science (JAIGS)"},{"key":"e_1_3_1_56_2","unstructured":"Alexey Kurakin Ian J. Goodfellow and Samy Bengio. 2017. Adversarial machine learning at scale. In Proceedings of the International Conference on Learning Representations (ICLR 2017). Available at: https:\/\/openreview.net\/forum?id=BJm4T4Kgx"},{"key":"e_1_3_1_57_2","article-title":"VTFR-AT: Adversarial training with visual transformation and feature robustness","author":"Li Xiang","year":"2024","unstructured":"Xiang Li, Changfei Zhao, Xinyang Deng, and Wen Jiang. 2024. VTFR-AT: Adversarial training with visual transformation and feature robustness. IEEE Transactions on Emerging Topics in Computational Intelligence 8, 4 (2024), 3129\u20133140.","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3636551"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","unstructured":"Tony Lindeberg. 2012. Scale invariant feature transform. Scholarpedia 7 5 (May 2012) 10491. 10.4249\/SCHOLARPEDIA.10491","DOI":"10.4249\/SCHOLARPEDIA.10491"},{"key":"e_1_3_1_60_2","unstructured":"David Fern\u00e1ndez Llorca Ronan Hamon Henrik Junklewitz Kathrin Grosse Lars Kunze Patrick Seiniger Robert Swaim Nick Reed Alexandre Alahi Emilia G\u00f3mez et\u00a0al. 2024. Testing autonomous vehicles and AI: Perspectives and challenges from cybersecurity transparency robustness and fairness. arXiv:2403.14641. Retrieved from https:\/\/arxiv.org\/abs\/2403.14641"},{"key":"e_1_3_1_61_2","unstructured":"Zelong Long Richard McCreadie and Muhammad Imran. 2023. CrisisViT: A robust vision transformer for crisis image classification. In Proceedings of the 20th International ISCRAM Conference Jaziar Radianti Ioannis Dokas Nicolas Lalone and Deepak Khazanchi (Eds.). University of Nebraska at Omaha Omaha USA 309\u2013319."},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00016"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-022-01665-y"},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00427"},{"key":"e_1_3_1_65_2","unstructured":"Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras and Adrian Vladu. 2018. Towards deep learning models resistant to adversarial attacks. In Proceedings of the International Conference on Learning Representations (ICLR 2018). https:\/\/openreview.net\/forum?id=rJzIBfZAb"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00774"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCKE57176.2022.9960090"},{"key":"e_1_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2013.6707049"},{"key":"e_1_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/WF-IoT58464.2023.10539404"},{"key":"e_1_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.3390\/app13095521"},{"key":"e_1_3_1_71_2","unstructured":"Susano Mingwin Yulong Shisu Yongshuai Wanwag and Sunshin Huing. 2024. Revolutionizing traffic sign recognition: Unveiling the potential of vision transformers. arXiv:2404.19066. Retrieved from https:\/\/arxiv.org\/abs\/2404.19066"},{"key":"e_1_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2012.2209421"},{"key":"e_1_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS46773.2023.10181988"},{"key":"e_1_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10723-023-09684-9"},{"key":"e_1_3_1_75_2","unstructured":"Amirhossein Nazeri Chunheng Zhao and Pierluigi Pisu. 2024. Evaluating the adversarial robustness of detection transformers. arXiv:2412.18718. Retrieved from https:\/\/arxiv.org\/abs\/2412.18718"},{"key":"e_1_3_1_76_2","article-title":"Physical adversarial attacks for surveillance: A survey","author":"Nguyen Kien","year":"2023","unstructured":"Kien Nguyen, Tharindu Fernando, Clinton Fookes, and Sridha Sridharan. 2023. Physical adversarial attacks for surveillance: A survey. IEEE Transactions on Neural Networks and Learning Systems 35, 12 (2023), 17036\u201317056.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_1_77_2","unstructured":"Keiron O\u2019shea and Ryan Nash. 2015. An introduction to convolutional neural networks. arXiv:1511.08458. Retrieved from https:\/\/arxiv.org\/abs\/1511.08458"},{"key":"e_1_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3053009"},{"key":"e_1_3_1_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"e_1_3_1_80_2","unstructured":"Maithra Raghu Thomas Unterthiner Simon Kornblith Chiyuan Zhang and Alexey Dosovitskiy. 2021. Do vision transformers see like convolutional neural networks? In Advances in Neural Information Processing Systems M. Ranzato A. Beygelzimer Y. Dauphin P.S. Liang and J. Wortman Vaughan (Eds.). Vol. 34. Curran Associates Inc. 12116\u201312128. Available at: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/652cf38361a209088302ba2b8b7f51e0-Paper.pdf"},{"key":"e_1_3_1_81_2","doi-asserted-by":"publisher","DOI":"10.3390\/app9050909"},{"key":"e_1_3_1_82_2","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","author":"Raghu Maithra","year":"2021","unstructured":"Maithra Raghu, Thomas Unterthiner, Simon Kornblith, Chiyuan Zhang, and Alexey Dosovitskiy. 2021. Do vision transformers see like convolutional neural networks? Proceedings of the 35th International Conference on Neural Information Processing Systems. 12116\u201312128.","journal-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems"},{"key":"e_1_3_1_83_2","doi-asserted-by":"publisher","DOI":"10.5220\/0005268904110418"},{"key":"e_1_3_1_84_2","unstructured":"Javier Rando Nasib Naimi Thomas Baumann and Max Mathys. 2022. Exploring adversarial attacks and defenses in vision transformers trained with DINO. arXiv:2206.06761. Retrieved from https:\/\/arxiv.org\/abs\/2206.06761"},{"key":"e_1_3_1_85_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447582"},{"key":"e_1_3_1_86_2","unstructured":"Mahdi Salmani Alireza Dehghanpour Farashah Mohammad Azizmalayeri Mahdi Amiri Navid Eslami Mohammad Taghi Manzuri and Mohammad Hossein Rohban. 2023. Blacksmith: Fast adversarial training of vision transformers via a mixture of single-step and multi-step methods. arXiv:2310.18975. Retrieved from https:\/\/arxiv.org\/abs\/2310.18975"},{"key":"e_1_3_1_87_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323651"},{"key":"e_1_3_1_88_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-52426-4"},{"key":"e_1_3_1_89_2","unstructured":"Novendra Setyawan Chi-Chia Sun Mao-Hsiu Hsu Wen-Kai Kuo and Jun-Wei Hsieh. 2025. MicroViT: A vision transformer with low complexity self attention for edge device. arXiv:2502.05800. Retrieved from https:\/\/arxiv.org\/abs\/2502.05800"},{"key":"e_1_3_1_90_2","article-title":"Adversarial training for free! In","author":"Shafahi Ali","year":"2019","unstructured":"Ali Shafahi, Mahyar Najibi, Mohammad Amin Ghiasi, Zheng Xu, John Dickerson, Christoph Studer, Larry S. Davis, Gavin Taylor, and Tom Goldstein. 2019. Adversarial training for free! In Proceedings of the 33rd International Conference on Neural Information Processing Systems.","journal-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems"},{"key":"e_1_3_1_91_2","volume-title":"Proceedings of the Neurips Safe Generative AI Workshop 2024","author":"Shao Mingzhen","unstructured":"Mingzhen Shao. 2024. Designing physical-world universal attacks on vision transformers. In Proceedings of the Neurips Safe Generative AI Workshop 2024."},{"key":"e_1_3_1_92_2","unstructured":"Rulin Shao Zhouxing Shi Jinfeng Yi Pin-Yu Chen and Cho-Jui Hsieh. 2022. On the adversarial robustness of vision transformers. Available at: https:\/\/openreview.net\/forum?id=O0g6uPDLW7"},{"key":"e_1_3_1_93_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2011.6033395"},{"key":"e_1_3_1_94_2","unstructured":"Akshayvarun Subramanya Aniruddha Saha Soroush Abbasi Koohpayegani Ajinkya Tejankar and Hamed Pirsiavash. 2022. Backdoor attacks on vision transformers. arXiv:2206.08477. Retrieved from https:\/\/arxiv.org\/abs\/2206.08477"},{"key":"e_1_3_1_95_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICAMMAET.2017.8186650"},{"key":"e_1_3_1_96_2","first-page":"18583","article-title":"Measuring robustness to natural distribution shifts in image classification","author":"Taori Rohan","year":"2020","unstructured":"Rohan Taori, Achal Dave, Vaishaal Shankar, Nicholas Carlini, Benjamin Recht, and Ludwig Schmidt. 2020. Measuring robustness to natural distribution shifts in image classification. In Proceedings of the 34th International Conference on Neural Information Processing Systems. 18583\u201318599.","journal-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems"},{"key":"e_1_3_1_97_2","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-60566-766-9.ch011"},{"key":"e_1_3_1_98_2","unstructured":"Shikhar Tuli Ishita Dasgupta Erin Grant and Thomas L. Griffiths. 2021. Are convolutional neural networks or transformers more like human vision? arXiv:2105.07197. Retrieved from https:\/\/arxiv.org\/abs\/2105.07197"},{"key":"e_1_3_1_99_2","article-title":"Attention is all you need","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems.","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"e_1_3_1_100_2","doi-asserted-by":"publisher","unstructured":"Donghua Wang Wen Yao Tingsong Jiang Guijian Tang and Xiaoqian Chen. 2022. A survey on physical adversarial attack in computer vision. arXiv preprint arXiv:2209.14262. Available at: 10.48550\/arXiv.2209.14262","DOI":"10.48550\/arXiv.2209.14262"},{"key":"e_1_3_1_101_2","doi-asserted-by":"publisher","unstructured":"Sinong Wang Belinda Z. Li Madian Khabsa Han Fang and Hao Ma. 2020. Linformer: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768. 10.48550\/arXiv.2006.04768","DOI":"10.48550\/arXiv.2006.04768"},{"key":"e_1_3_1_102_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547989"},{"key":"e_1_3_1_103_2","article-title":"Quantformer: Learning extremely low-precision vision transformers","author":"Wang Ziwei","year":"2022","unstructured":"Ziwei Wang, Changyuan Wang, Xiuwei Xu, Jie Zhou, and Jiwen Lu. 2022. Quantformer: Learning extremely low-precision vision transformers. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 7 (2022), 8813\u20138826.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_1_104_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20169"},{"key":"e_1_3_1_105_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_18"},{"key":"e_1_3_1_106_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.01.003"},{"key":"e_1_3_1_107_2","first-page":"11492","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Xu Han","year":"2021","unstructured":"Han Xu, Xiaorui Liu, Yaxin Li, Anil Jain, and Jiliang Tang. 2021. To be robust or to be fair: Towards fairness in adversarial training. In Proceedings of the International Conference on Machine Learning. PMLR, 11492\u201311501."},{"key":"e_1_3_1_108_2","article-title":"Vision transformer with attentive pooling for robust facial expression recognition","author":"Xue Fanglei","year":"2022","unstructured":"Fanglei Xue, Qiangchang Wang, Zichang Tan, Zhongsong Ma, and Guodong Guo. 2022. Vision transformer with attentive pooling for robust facial expression recognition. IEEE Transactions on Affective Computing 14, 4 (2022), 3244\u20133256.","journal-title":"IEEE Transactions on Affective Computing"},{"key":"e_1_3_1_109_2","first-page":"52936","article-title":"VLATTACK: Multimodal adversarial attacks on vision-language tasks via pre-trained models","author":"Yin Ziyi","year":"2023","unstructured":"Ziyi Yin, Muchao Ye, Tianrong Zhang, Tianyu Du, Jinguo Zhu, Han Liu, Jinghui Chen, Ting Wang, and Fenglong Ma. 2023. VLATTACK: Multimodal adversarial attacks on vision-language tasks via pre-trained models. In Proceedings of the 37th International Conference on Neural Information Processing Systems. 52936\u201352956.","journal-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems"},{"key":"e_1_3_1_110_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02170"},{"key":"e_1_3_1_111_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87358-5_12"},{"key":"e_1_3_1_112_2","unstructured":"Zheng Yuan Jie Zhang and Shiguang Shan. 2024. FullLoRA-AT: Efficiently boosting the robustness of pretrained vision transformers. arXiv:2401.01752. Retrieved from https:\/\/arxiv.org\/abs\/2401.01752"},{"key":"e_1_3_1_113_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"e_1_3_1_114_2","unstructured":"Lin Zehui Pengfei Liu Luyao Huang Junkun Chen Xipeng Qiu and Xuanjing Huang. 2019. DropAttention: A regularization method for fully-connected self-attention networks. arXiv:1907.11065. Retrieved from https:\/\/arxiv.org\/abs\/1907.11065"},{"key":"e_1_3_1_115_2","article-title":"Transformer fusion and residual learning group classifier loss for long-tailed traffic sign detection","author":"Zeng Guanjie","year":"2024","unstructured":"Guanjie Zeng, Weiguo Huang, Yinjie Wang, Xiang Wang, and E. Wenjuan. 2024. Transformer fusion and residual learning group classifier loss for long-tailed traffic sign detection. IEEE Sensors Journal 24, 7 (2024), 10551\u201310560.","journal-title":"IEEE Sensors Journal"},{"key":"e_1_3_1_116_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13050880"},{"key":"e_1_3_1_117_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01575"},{"key":"e_1_3_1_118_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28541"},{"key":"e_1_3_1_119_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.animal.2023.100886"},{"key":"e_1_3_1_120_2","first-page":"54111","article-title":"On evaluating adversarial robustness of large vision-language models","author":"Zhao Yunqing","year":"2023","unstructured":"Yunqing Zhao, Tianyu Pang, Chao Du, Xiao Yang, Chongxuan Li, Ngai-Man Man Cheung, and Min Lin. 2023. On evaluating adversarial robustness of large vision-language models. In Proceedings of the 37th International Conference on Neural Information Processing Systems. 54111\u201354138.","journal-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems"},{"key":"e_1_3_1_121_2","doi-asserted-by":"crossref","unstructured":"Yuping Zheng and Weiwei Jiang. 2022. Evaluation of vision transformers for traffic sign classification. Wireless Communications and Mobile Computing 2022 1 (2022) 3041117.","DOI":"10.1155\/2022\/3041117"},{"key":"e_1_3_1_122_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.232"}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3729167","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3729167","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:48Z","timestamp":1750295928000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3729167"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,7]]},"references-count":121,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10,31]]}},"alternative-id":["10.1145\/3729167"],"URL":"https:\/\/doi.org\/10.1145\/3729167","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,7]]},"assertion":[{"value":"2024-09-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}