{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T12:49:06Z","timestamp":1766753346996,"version":"3.48.0"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T00:00:00Z","timestamp":1766707200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T00:00:00Z","timestamp":1766707200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Central Government Guided Local Funds for Science and Technology Development","award":["No.216Z0301G"],"award-info":[{"award-number":["No.216Z0301G"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No.62476235"],"award-info":[{"award-number":["No.62476235"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003787","name":"Hebei Natural Science Foundation","doi-asserted-by":"crossref","award":["No.F2023203012"],"award-info":[{"award-number":["No.F2023203012"]}],"id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Innovation Capability Improvement Plan Project of Hebei Province","award":["No.22567626H"],"award-info":[{"award-number":["No.22567626H"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-025-08170-1","type":"journal-article","created":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T12:46:56Z","timestamp":1766753216000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Boosting video adversarial attacks with refined perturbations"],"prefix":"10.1007","volume":"82","author":[{"given":"Xueqiang","family":"Han","sequence":"first","affiliation":[]},{"given":"Shi","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Qing","family":"Tian","sequence":"additional","affiliation":[]},{"given":"Shihui","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,12,26]]},"reference":[{"key":"8170_CR1","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings"},{"key":"8170_CR2","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol 2016-December, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"8170_CR3","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N (2021) An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale. In: ICLR 2021 - 9th International Conference on Learning Representations"},{"issue":"6","key":"8170_CR4","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84\u201390","journal-title":"Commun ACM"},{"issue":"2","key":"8170_CR5","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1007\/s11227-024-06663-z","volume":"81","author":"N Osmani","year":"2025","unstructured":"Osmani N, Esmaeeli E, Rezayi S (2025) Fusion strategies for deep convolutional neural network representations in histopathological image classification. J Supercomput 81(2):66","journal-title":"J Supercomput"},{"issue":"2","key":"8170_CR6","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TPAMI.2024.3429387","volume":"47","author":"K-Y Lin","year":"2025","unstructured":"Lin K-Y, Zhou J, Zheng W-S (2025) Human-centric transformer for domain adaptive action recognition. IEEE Trans Pattern Anal Mach Intell 47(2):679\u2013696","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"9","key":"8170_CR7","doi-asserted-by":"publisher","first-page":"12430","DOI":"10.1007\/s11227-024-05910-7","volume":"80","author":"A Mira","year":"2024","unstructured":"Mira A, Hellwich O (2024) Deep learning models beyond temporal frame-wise features for hand gesture video recognition. J Supercomput 80(9):12430\u201312462","journal-title":"J Supercomput"},{"key":"8170_CR8","doi-asserted-by":"crossref","unstructured":"Lu Z, Shuai B, Chen Y, Xu Z, Modolo D (2024) Self-supervised multi-object tracking with path consistency. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp 19016\u201319026","DOI":"10.1109\/CVPR52733.2024.01799"},{"issue":"13","key":"8170_CR9","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1007\/s11227-025-07730-9","volume":"81","author":"H Liang","year":"2025","unstructured":"Liang H, Xu M, Zhang Q, Shao M (2025) Multi-cue sort: integrating weak cues with appearance and motion for multi-object tracking. J Supercomput 81(13):66","journal-title":"J Supercomput"},{"key":"8170_CR10","doi-asserted-by":"crossref","unstructured":"Shibuya M, Sumikura S, Sakurada K (2020) Privacy Preserving Visual SLAM","DOI":"10.1007\/978-3-030-58542-6_7"},{"key":"8170_CR11","unstructured":"Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan D, Goodfellow I, Fergus R (2013) Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199"},{"key":"8170_CR12","doi-asserted-by":"crossref","unstructured":"Moosavi-Dezfooli S-M, Fawzi A, Frossard P (2016) Deepfool: A simple and accurate method to fool deep neural networks. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol 2016-December, pp 2574\u20132582","DOI":"10.1109\/CVPR.2016.282"},{"key":"8170_CR13","doi-asserted-by":"crossref","unstructured":"Wei X, Zhu J, Yuan S, Su H (2019) Sparse adversarial perturbations for videos. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp 8973\u20138980","DOI":"10.1609\/aaai.v33i01.33018973"},{"key":"8170_CR14","doi-asserted-by":"crossref","unstructured":"Wei Z, Chen J, Wei X, Jiang L, Chua T-S, Zhou F, Jiang Y-G (2020) Heuristic black-box adversarial attacks on video recognition models. In: AAAI 2020 - 34th AAAI Conference on Artificial Intelligence, pp 12338\u201312345","DOI":"10.1609\/aaai.v34i07.6918"},{"issue":"6","key":"8170_CR15","doi-asserted-by":"publisher","first-page":"1459","DOI":"10.1007\/s11263-022-01604-w","volume":"130","author":"X Wei","year":"2022","unstructured":"Wei X, Yan H, Li B (2022) Sparse black-box video attack with reinforcement learning. Int J Comput Vision 130(6):1459\u20131473","journal-title":"Int J Comput Vision"},{"key":"8170_CR16","doi-asserted-by":"crossref","unstructured":"Wei Z, Chen J, Zhang H, Jiang L, Jiang Y-G (2022) Adaptive temporal grouping for black-box adversarial attacks on videos. In: Proceedings of the 2022 International Conference on Multimedia Retrieval, pp 587\u2013593","DOI":"10.1145\/3512527.3531411"},{"key":"8170_CR17","unstructured":"Liu Y, Chen X, Liu C, Song D (2017) Delving into transferable adversarial examples and black-box attacks. In: 5th International Conference on Learning Representations, ICLR 2017 - Conference Track Proceedings"},{"key":"8170_CR18","doi-asserted-by":"crossref","unstructured":"Dong Y, Liao F, Pang T, Su H, Zhu J, Hu X, Li J (2018) Boosting adversarial attacks with momentum. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp 9185\u20139193","DOI":"10.1109\/CVPR.2018.00957"},{"key":"8170_CR19","unstructured":"Ge Z, Liu H, Wang X, Shang F, Liu Y (2023) Boosting adversarial transferability by achieving flat local maxima. In: Advances in Neural Information Processing Systems, vol 36"},{"key":"8170_CR20","doi-asserted-by":"crossref","unstructured":"Zhang J, Huang Y, Xu Z, Wu W, Lyu MR (2024) Improving the adversarial transferability of vision transformers with virtual dense connection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 38, pp 7133\u20137141","DOI":"10.1609\/aaai.v38i7.28541"},{"key":"8170_CR21","doi-asserted-by":"crossref","unstructured":"Wei Z, Chen J, Wu Z, Jiang Y-G (2023) Enhancing the self-universality for transferable targeted attacks. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol 2023-June, pp 12281\u201312290","DOI":"10.1109\/CVPR52729.2023.01182"},{"key":"8170_CR22","doi-asserted-by":"crossref","unstructured":"Wang K, He X, Wang W, Wang X (2024) Boosting adversarial transferability by block shuffle and rotation. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR52733.2024.02297"},{"key":"8170_CR23","doi-asserted-by":"crossref","unstructured":"Zhu R, Zhang Z, Liu Z, Xu C, Liang S (2024) Learning to transform dynamically for better adversarial transferability. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp 24273\u201324283","DOI":"10.1109\/CVPR52733.2024.02291"},{"key":"8170_CR24","doi-asserted-by":"crossref","unstructured":"Fang Z, Wang R, Huang T, Jing L (2024) Strong transferable adversarial attacks via ensembled asymptotically normal distribution learning. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp 24841\u201324850","DOI":"10.1109\/CVPR52733.2024.02346"},{"key":"8170_CR25","doi-asserted-by":"crossref","unstructured":"Wei Z, Chen J, Wu Z, Jiang Y-G (2022) Cross-modal transferable adversarial attacks from images to videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 15064\u201315073","DOI":"10.1109\/CVPR52688.2022.01464"},{"key":"8170_CR26","doi-asserted-by":"crossref","unstructured":"Wei Z, Chen J, Wu Z, Jiang Y-G (2022) Boosting the transferability of video adversarial examples via temporal translation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 36, pp 2659\u20132667","DOI":"10.1609\/aaai.v36i3.20168"},{"key":"8170_CR27","unstructured":"Goodfellow IJ, Shlens J, Szegedy C (2015) Explaining and harnessing adversarial examples. In: 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings"},{"issue":"8","key":"8170_CR28","doi-asserted-by":"publisher","first-page":"5663","DOI":"10.1109\/TPAMI.2024.3367773","volume":"46","author":"Z Yuan","year":"2024","unstructured":"Yuan Z, Zhang J, Jiang Z, Li L, Shan S (2024) Adaptive perturbation for adversarial attack. IEEE Trans Pattern Anal Mach Intell 46(8):5663\u20135676","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8170_CR29","unstructured":"Kurakin A, Goodfellow IJ, Bengio S (2017) Adversarial examples in the physical world. In: 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings"},{"key":"8170_CR30","unstructured":"Madry A, Makelov A, Schmidt L, Tsipras D, Vladu A (2018) Towards deep learning models resistant to adversarial attacks. In: 6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings"},{"key":"8170_CR31","doi-asserted-by":"crossref","unstructured":"Carlini N, Wagner D (2017) Towards evaluating the robustness of neural networks. In: Proceedings - IEEE Symposium on Security and Privacy, vol 0, pp 39\u201357","DOI":"10.1109\/SP.2017.49"},{"key":"8170_CR32","unstructured":"Wu D, Wang Y, Xia S-T, Bailey J, Ma X (2020) Skip connections matter: On the transferability of adversarial examples generated with resnets. In: 8th International Conference on Learning Representations, ICLR 2020"},{"key":"8170_CR33","doi-asserted-by":"crossref","unstructured":"Xie C, Zhang Z, Zhou Y, Bai S, Wang J, Ren Z, Yuille AL (2019) Improving transferability of adversarial examples with input diversity. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp 2725\u20132734","DOI":"10.1109\/CVPR.2019.00284"},{"key":"8170_CR34","doi-asserted-by":"crossref","unstructured":"Dong Y, Pang T, Su H, Zhu J (2019) Evading defenses to transferable adversarial examples by translation-invariant attacks. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp 4307\u20134316","DOI":"10.1109\/CVPR.2019.00444"},{"key":"8170_CR35","unstructured":"Lin J, Song C, He K, Wang L, Hopcroft JE (2020) Nesterov accelerated gradient and scale invariance for adversarial attacks. In: 8th International Conference on Learning Representations, ICLR 2020"},{"key":"8170_CR36","doi-asserted-by":"crossref","unstructured":"Pony R, Naeh I, Mannor S (2021) Over-the-air adversarial flickering attacks against video recognition networks. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp 515\u2013524","DOI":"10.1109\/CVPR46437.2021.00058"},{"key":"8170_CR37","doi-asserted-by":"crossref","unstructured":"Chen Z, Xie L, Pang S, He Y, Tian Q (2021) Appending adversarial frames for universal video attack. In: Proceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021, pp 3198\u20133207","DOI":"10.1109\/WACV48630.2021.00324"},{"key":"8170_CR38","doi-asserted-by":"crossref","unstructured":"Wang R, Guo Y, Wang Y (2023) Global-local characteristic excited cross-modal attacks from images to videos. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 37, pp 2635\u20132643","DOI":"10.1609\/aaai.v37i2.25362"},{"issue":"5","key":"8170_CR39","doi-asserted-by":"publisher","first-page":"3772","DOI":"10.1109\/TPAMI.2023.3347835","volume":"46","author":"Z Wei","year":"2024","unstructured":"Wei Z, Chen J, Wu Z, Jiang Y-G (2024) Adaptive cross-modal transferable adversarial attacks from images to videos. IEEE Trans Pattern Anal Mach Intell 46(5):3772\u20133783","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8170_CR40","doi-asserted-by":"crossref","unstructured":"Chen K, Wei Z, Chen J, Wu Z, Jiang Y-G (2023) Gcma: Generative cross-modal transferable adversarial attacks from images to videos. In: MM 2023 - Proceedings of the 31st ACM International Conference on Multimedia, pp 698\u2013708","DOI":"10.1145\/3581783.3612110"},{"key":"8170_CR41","unstructured":"Wang X, Ren J, Lin S, Zhu X, Wang Y, Zhang Q (2021) A unified approach to interpreting and boosting adversarial transferability. In: ICLR 2021 - 9th International Conference on Learning Representations"},{"key":"8170_CR42","doi-asserted-by":"crossref","unstructured":"Hwang J, Kim J-H, Choi J-H, Lee J-S (2021) Just one moment: Structural vulnerability of deep action recognition against one frame attack. In: Proceedings of the IEEE International Conference on Computer Vision, pp 7648\u20137656","DOI":"10.1109\/ICCV48922.2021.00757"},{"key":"8170_CR43","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 6299\u20136308","DOI":"10.1109\/CVPR.2017.502"},{"key":"8170_CR44","unstructured":"Soomro K, Zamir AR, Shah M (2012) Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402"},{"key":"8170_CR45","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, He K (2018) Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7794\u20137803","DOI":"10.1109\/CVPR.2018.00813"},{"key":"8170_CR46","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Fan H, Malik J, He K (2019) Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 6202\u20136211","DOI":"10.1109\/ICCV.2019.00630"},{"key":"8170_CR47","doi-asserted-by":"crossref","unstructured":"Yang C, Xu Y, Shi J, Dai B, Zhou B (2020) Temporal pyramid network for action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 591\u2013600","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"8170_CR48","doi-asserted-by":"crossref","unstructured":"Arnab A, Dehghani M, Heigold G, Sun C, Lui M, Schmid C (2021) Vivit: A video vision transformer. In: Proceedings of the IEEE International Conference on Computer Vision, pp 6816\u20136826","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"8170_CR49","unstructured":"Bertasius G, Wang H, Torresani L (2021) Is space-time attention all you need for video understanding? In: Proceedings of Machine Learning Research, vol 139, pp 813\u2013824"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-08170-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-025-08170-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-08170-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T12:47:02Z","timestamp":1766753222000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-025-08170-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,26]]},"references-count":49,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["8170"],"URL":"https:\/\/doi.org\/10.1007\/s11227-025-08170-1","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,26]]},"assertion":[{"value":"16 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"32"}}