{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T06:56:01Z","timestamp":1768719361131,"version":"3.49.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T00:00:00Z","timestamp":1700524800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T00:00:00Z","timestamp":1700524800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972458"],"award-info":[{"award-number":["61972458"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LZ23F020002"],"award-info":[{"award-number":["LZ23F020002"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis. Comput. Ind. Biomed. Art"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Deep neural networks are vulnerable to attacks from adversarial inputs. Corresponding attack research on human pose estimation (HPE), particularly for body joint detection, has been largely unexplored. Transferring classification-based attack methods to body joint regression tasks is not straightforward. Another issue is that the attack effectiveness and imperceptibility contradict each other. To solve these issues, we propose local imperceptible attacks on HPE networks. In particular, we reformulate imperceptible attacks on body joint regression into a constrained maximum allowable attack. Furthermore, we approximate the solution using iterative gradient-based strength refinement and greedy-based pixel selection. Our method crafts effective perceptual adversarial attacks that consider both human perception and attack effectiveness. We conducted a series of imperceptible attacks against state-of-the-art HPE methods, including HigherHRNet, DEKR, and ViTPose. The experimental results demonstrate that the proposed method achieves excellent imperceptibility while maintaining attack effectiveness by significantly reducing the number of perturbed pixels. Approximately 4% of the pixels can achieve sufficient attacks on HPE.<\/jats:p>","DOI":"10.1186\/s42492-023-00148-1","type":"journal-article","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T05:31:25Z","timestamp":1700544685000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Local imperceptible adversarial attacks against human pose estimation networks"],"prefix":"10.1186","volume":"6","author":[{"given":"Fuchang","family":"Liu","sequence":"first","affiliation":[]},{"given":"Shen","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Caiping","family":"Yan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5479-9060","authenticated-orcid":false,"given":"Yongwei","family":"Miao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,21]]},"reference":[{"key":"148_CR1","doi-asserted-by":"publisher","unstructured":"Carlini N, Wagner D (2017) Towards evaluating the robustness of neural networks. In: Proceedings of the 2017 IEEE symposium on security and privacy, IEEE, San Jose, 22-26 May 2017. https:\/\/doi.org\/10.1109\/SP.2017.49","DOI":"10.1109\/SP.2017.49"},{"key":"148_CR2","doi-asserted-by":"publisher","unstructured":"Kurakin A, Goodfellow IJ, Bengio S (2018) Adversarial examples in the physical world. In: Yampolskiy RV (ed) In Artificial intelligence safety and security, 1st edn. Taylor & Francis Group, New York. https:\/\/doi.org\/10.1201\/9781351251389-8","DOI":"10.1201\/9781351251389-8"},{"issue":"5","key":"148_CR3","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1109\/TEVC.2019.2890858","volume":"23","author":"JW Su","year":"2019","unstructured":"Su JW, Vargas DV, Sakurai K (2019) One pixel attack for fooling deep neural networks. IEEE Trans Evol Comput 23(5):828-841. https:\/\/doi.org\/10.1109\/TEVC.2019.2890858","journal-title":"IEEE Trans Evol Comput"},{"key":"148_CR4","doi-asserted-by":"publisher","unstructured":"Kurakin A, Goodfellow I, Bengio S (2016) Adversarial machine learning at scale. arXiv, 2016. https:\/\/doi.org\/10.48550\/arXiv.1611.01236","DOI":"10.48550\/arXiv.1611.01236"},{"key":"148_CR5","unstructured":"Madry A, Makelov A, Schmidt L, Tsipras D, Vladu A (2018) Towards deep learning models resistant to adversarial attacks. In: Proceedings of the 6th international conference on learning representations, OpenReview.net, Vancouver, 30 April-3 May 2018"},{"key":"148_CR6","doi-asserted-by":"publisher","unstructured":"Moosavi-Dezfooli SM, Fawzi A, Frossard P (2016) DeepFool: a simple and accurate method to fool deep neural networks. In: Proceedings of the 2016 IEEE conference on computer vision and pattern recognition, IEEE, Las Vegas, 27-30 June 2016. https:\/\/doi.org\/10.1109\/CVPR.2016.282","DOI":"10.1109\/CVPR.2016.282"},{"key":"148_CR7","doi-asserted-by":"publisher","unstructured":"Chen PY, Zhang H, Sharma Y, Yi JF, Hsieh CJ (2017) ZOO: zeroth order optimization based black-box attacks to deep neural networks without training substitute models. In: Proceedings of the 10th ACM workshop on artificial intelligence and security, ACM, Dallas, 3 November 2017. https:\/\/doi.org\/10.1145\/3128572.3140448","DOI":"10.1145\/3128572.3140448"},{"key":"148_CR8","volume-title":"Decision-based adversarial attacks: reliable attacks against black-box machine learning models. Proceedings of the 6th international conference on learning representations","author":"W Brendel","year":"2018","unstructured":"Brendel W, Rauber J, Bethge M (2018) Decision-based adversarial attacks: reliable attacks against black-box machine learning models. In: Proceedings of the 6th international conference on learning representations, OpenReview.net, Vancouver, 30 April-3 May 2018"},{"key":"148_CR9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00444","volume-title":"Evading defenses to transferable adversarial examples by translation-invariant attacks. In: Proceedings of the 2019 IEEE\/CVF conference on computer vision and pattern recognition","author":"YP Dong","year":"2019","unstructured":"Dong YP, Pang TY, Su H, Zhu J (2019) Evading defenses to transferable adversarial examples by translation-invariant attacks. In: Proceedings of the 2019 IEEE\/CVF conference on computer vision and pattern recognition, IEEE, Long Beach, 15-20 June 2019. https:\/\/doi.org\/10.1109\/CVPR.2019.00444"},{"issue":"4","key":"148_CR10","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600-612. https:\/\/doi.org\/10.1109\/TIP.2003.819861","journal-title":"IEEE Trans Image Process"},{"key":"148_CR11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068","volume-title":"The unreasonable effectiveness of deep features as a perceptual metric. Proceedings of the 2018 IEEE conference on computer vision and pattern recognition","author":"R Zhang","year":"2018","unstructured":"Zhang R, Isola P, Efros AA, Shechtman E, Wang O (2018) The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the 2018 IEEE conference on computer vision and pattern recognition, IEEE, Salt Lake City, 18-23 June 2018. https:\/\/doi.org\/10.1109\/CVPR.2018.00068"},{"key":"148_CR12","volume-title":"In: Proceedings of the 33th Conference on Advances in Neural Information Processing Systems","author":"C Laidlaw","year":"2019","unstructured":"Laidlaw C, Feizi S. Functional adversarial attacks (2019) In: Proceedings of the 33th Conference on Advances in Neural Information Processing Systems, OpenReview.net, Vancouver, 8-14 December 2019"},{"key":"148_CR13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214","volume-title":"DeepPose: human pose estimation via deep neural networks. Proceedings of the 2014 IEEE conference on computer vision and pattern recognition","author":"A Toshev","year":"2014","unstructured":"Toshev A, Szegedy C (2014) DeepPose: human pose estimation via deep neural networks. In: Proceedings of the 2014 IEEE conference on computer vision and pattern recognition, IEEE, Columbus, 23-28 June 2014. https:\/\/doi.org\/10.1109\/CVPR.2014.214"},{"key":"148_CR14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322","volume-title":"Mask R-CNN. Proceedings of the 2017 IEEE international conference on computer vision","author":"KM He","year":"2017","unstructured":"He KM, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask R-CNN. In: Proceedings of the 2017 IEEE international conference on computer vision, IEEE, Venice, 22-29 October 2017. https:\/\/doi.org\/10.1109\/ICCV.2017.322"},{"key":"148_CR15","volume-title":"Joint training of a convolutional network and a graphical model for human pose estimation. Proceedings of the 27th international conference on neural information processing systems","author":"J Tompson","year":"2014","unstructured":"Tompson J, Jain A, LeCun Y, Bregler C (2014) Joint training of a convolutional network and a graphical model for human pose estimation. In: Proceedings of the 27th international conference on neural information processing systems, MIT Press, Montreal, 8-13 December 2014"},{"key":"148_CR16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584","volume-title":"Deep high-resolution representation learning for human pose estimation. Proceedings of the 2019 IEEE\/CVF conference on computer vision and pattern recognition","author":"K Sun","year":"2019","unstructured":"Sun K, Xiao B, Liu D, Wang JD (2019) Deep high-resolution representation learning for human pose estimation. In: Proceedings of the 2019 IEEE\/CVF conference on computer vision and pattern recognition, IEEE, Long Beach, 15-20 June 2019. https:\/\/doi.org\/10.1109\/CVPR.2019.00584"},{"key":"148_CR17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00543","volume-title":"HigherHRNet: scale-aware representation learning for bottom-up human pose estimation. Proceedings of the 2020 IEEE\/CVF conference on computer vision and pattern recognition","author":"BW Cheng","year":"2020","unstructured":"Cheng BW, Xiao B, Wang JD, Shi HH, Huang TS, Zhang L (2020) HigherHRNet: scale-aware representation learning for bottom-up human pose estimation. In: Proceedings of the 2020 IEEE\/CVF conference on computer vision and pattern recognition, IEEE, Seattle, 13-19 June 2020. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00543"},{"key":"148_CR18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01444","volume-title":"Bottom-up human pose estimation via disentangled keypoint regression. Proceedings of the 2021 IEEE\/CVF conference on computer vision and pattern recognition","author":"ZG Geng","year":"2021","unstructured":"Geng ZG, Sun K, Xiao B, Zhang ZX, Wang JD (2021) Bottom-up human pose estimation via disentangled keypoint regression. In: Proceedings of the 2021 IEEE\/CVF conference on computer vision and pattern recognition, IEEE, Nashville, 20-25 June 2021. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01444"},{"key":"148_CR19","doi-asserted-by":"publisher","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D et al (2014) Microsoft COCO: common objects in context. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer vision-ECCV 2014. 13th European conference, Zurich, September 2014. Lecture notes in computer science (Image processing, computer vision, pattern recognition, and graphics), vol 8693. Springer, Cham, p 740. https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"12","key":"148_CR20","doi-asserted-by":"publisher","first-page":"2878","DOI":"10.1109\/TPAMI.2012.261","volume":"35","author":"Y Yang","year":"2013","unstructured":"Yang Y, Ramanan D (2013) Articulated human detection with flexible mixtures of parts. IEEE Trans Pattern Anal Mach Intell 35(12):2878-2890. https:\/\/doi.org\/10.1109\/TPAMI.2012.261","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"148_CR21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01168","volume-title":"When human pose estimation meets robustness: adversarial algorithms and benchmarks. Proceedings of the 2021 IEEE\/CVF conference on computer vision and pattern recognition","author":"JH Wang","year":"2021","unstructured":"Wang JH, Jin S, Liu WT, Liu WZ, Qian C, Luo P (2021) When human pose estimation meets robustness: adversarial algorithms and benchmarks. In: Proceedings of the 2021 IEEE\/CVF conference on computer vision and pattern recognition, IEEE, Nashville, 20-25 June 2021. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01168"},{"key":"148_CR22","volume-title":"On the robustness of human pose estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops","author":"N Jain","year":"2019","unstructured":"Jain N, Shah S, Kumar A, Jain A (2019) On the robustness of human pose estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, IEEE, Long Beach, 16-20 June 2019"},{"issue":"4","key":"148_CR23","doi-asserted-by":"publisher","first-page":"1609","DOI":"10.1109\/TNNLS.2020.3043002","volume":"33","author":"J Liu","year":"2022","unstructured":"Liu J, Akhtar N, Mian A (2022) Adversarial attack on skeleton-based human action recognition. IEEE Trans Neural Netw Learn Syst 33(4):1609-1622. https:\/\/doi.org\/10.1109\/TNNLS.2020.3043002","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"148_CR24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00751","volume-title":"BASAR: black-box attack on skeletal action recognition. Proceedings of the 2021 IEEE\/CVF conference on computer vision and pattern recognition","author":"YF Diao","year":"2021","unstructured":"Diao YF, Shao TJ, Yang YL, Zhou K, Wang H (2021) BASAR: black-box attack on skeletal action recognition. In: Proceedings of the 2021 IEEE\/CVF conference on computer vision and pattern recognition, IEEE, Nashville, 20-25 June 2021. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00751"},{"key":"148_CR25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01442","volume-title":"Understanding the robustness of skeleton-based action recognition under adversarial attack. Proceedings of the 2021 IEEE\/CVF conference on computer vision and pattern recognition","author":"H Wang","year":"2021","unstructured":"Wang H, He FX, Peng ZX, Shao TJ, Yang YL, Zhou K et al (2021) Understanding the robustness of skeleton-based action recognition under adversarial attack. In: Proceedings of the 2021 IEEE\/CVF conference on computer vision and pattern recognition, IEEE, Nashville, 20-25 June 2021. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01442"},{"key":"148_CR26","doi-asserted-by":"publisher","unstructured":"Wang H, Diao YF, Tan ZC, Guo GD (2023) Defending black-box skeleton-based human activity classifiers. In: Proceedings of the thirty-seventh AAAI conference on artificial intelligence and thirty-fifth conference on innovative applications of artificial intelligence and thirteenth symposium on educational advances in artificial intelligence, AAAI Press, Washington, 7-14 February 2023. https:\/\/doi.org\/10.1609\/aaai.v37i2.25352","DOI":"10.1609\/aaai.v37i2.25352"},{"issue":"12","key":"148_CR27","doi-asserted-by":"publisher","first-page":"1458","DOI":"10.1364\/JOSA.70.001458","volume":"70","author":"GE Legge","year":"1980","unstructured":"Legge GE, Foley JM (1980) Contrast masking in human vision. J Opt Soc Am 70(12):1458-1471. https:\/\/doi.org\/10.1364\/JOSA.70.001458","journal-title":"J Opt Soc Am"},{"key":"148_CR28","doi-asserted-by":"publisher","unstructured":"Luo B, Liu YN, Wei LX, Xu Q (2018) Towards imperceptible and robust adversarial example attacks against neural networks. In: Proceedings of the thirty-second AAAI conference on artificial intelligence and thirtieth innovative applications of artificial intelligence conference and eighth AAAI symposium on educational advances in artificial intelligence, AAAI Press, New Orleans, 2-7 February 2018. https:\/\/doi.org\/10.1609\/aaai.v32i1.11499","DOI":"10.1609\/aaai.v32i1.11499"},{"key":"148_CR29","volume-title":"ViTPose: simple vision transformer baselines for human pose estimation. In: Proceedings of the 36th Conference on Advances in Neural Information Processing Systems","author":"YF Xu","year":"2022","unstructured":"Xu YF, Zhang J, Zhang QM, Tao DC (2022) ViTPose: simple vision transformer baselines for human pose estimation. In: Proceedings of the 36th Conference on Advances in Neural Information Processing Systems, OpenReview.net, New Orleans, 8-14 December 2022"}],"container-title":["Visual Computing for Industry, Biomedicine, and Art"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s42492-023-00148-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s42492-023-00148-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s42492-023-00148-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T05:32:23Z","timestamp":1700544743000},"score":1,"resource":{"primary":{"URL":"https:\/\/vciba.springeropen.com\/articles\/10.1186\/s42492-023-00148-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,21]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["148"],"URL":"https:\/\/doi.org\/10.1186\/s42492-023-00148-1","relation":{},"ISSN":["2524-4442"],"issn-type":[{"value":"2524-4442","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,21]]},"assertion":[{"value":"30 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 October 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 November 2023","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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"22"}}