{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T09:55:32Z","timestamp":1768643732657,"version":"3.49.0"},"reference-count":25,"publisher":"Walter de Gruyter GmbH","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Beijing Natural Science Foundation","award":["L222014"],"award-info":[{"award-number":["L222014"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Deep learning techniques have been widely used in various fields. However, they face significant security challenges due to the existence of adversarial examples. Traditional black-box adversarial attack methods mainly rely on swarm intelligence optimization algorithms to identify optimal perturbation pixels, which requires intensive computational resources. In some typical applications such as medical image recognition, public datasets are often used to train deep learning models. It is worth noting that such dataset inherently contains some basis features for deep learning models to learn discriminative representations. And these features can serve as critical cues for constructing adversarial samples. Inspired by this observation, a novel adversarial attack method was proposed. First, some sensitive locations are identified within the dataset without querying the target model. Moreover, the adversarial attack samples are constructed based on these locations. Different from white-box and black-box attack, dataset characteristics are utilized to construct adversarial attack samples. The proposed method investigates naturally occurring vulnerabilities in the data, offering new insights for enhancing data augmentation techniques and attack strategies, while also providing a promising direction for improving model robustness. Experimental results demonstrate that this method can achieve attack effectiveness comparable to the Particle Swarm Optimization (PSO) algorithm.<\/jats:p>","DOI":"10.1515\/jisys-2025-0076","type":"journal-article","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T10:25:56Z","timestamp":1768559156000},"source":"Crossref","is-referenced-by-count":0,"title":["An adversarial attack method based on pixel location characteristics"],"prefix":"10.1515","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5693-0408","authenticated-orcid":false,"given":"Qin","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Information of Third Medical Center , Chinese PLA General Hospital , Beijing 100039 , China"}]},{"given":"Jiuhong","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Information of Third Medical Center , Chinese PLA General Hospital , Beijing 100039 , China"}]},{"given":"Xian","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Information of Third Medical Center , Chinese PLA General Hospital , Beijing 100039 , China"}]},{"given":"Tongbo","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Information of Third Medical Center , Chinese PLA General Hospital , Beijing 100039 , China"}]},{"given":"Yingzhen","family":"Du","sequence":"additional","affiliation":[{"name":"Department of Disease Control and Prevention , The Second Medical Center and National Clinical Research Center for Geriatric Diseases, Chinese PLA , Beijing , 100089 , China"}]}],"member":"374","published-online":{"date-parts":[[2026,1,15]]},"reference":[{"key":"2026011611150954571_j_jisys-2025-0076_ref_001","doi-asserted-by":"crossref","unstructured":"C. Li, H. Wang, W. Yao, and T. Jiang, \u201cAdversarial attacks in computer vision: A survey,\u201d J.\u00a0Membr. Comput., vol.\u00a06, no. 2, pp.\u00a0130\u2013147, 2024, https:\/\/doi.org\/10.1007\/s41965-024-00142-3.","DOI":"10.1007\/s41965-024-00142-3"},{"key":"2026011611150954571_j_jisys-2025-0076_ref_002","doi-asserted-by":"crossref","unstructured":"F. Croce and M. Hein, \u201cSparse and imperceivable adversarial attacks,\u201d in Proc. of the IEEE\/CVF International Conf. on Computer Vision, Seol, Korea, 2019, pp.\u00a04724\u20134732.","DOI":"10.1109\/ICCV.2019.00482"},{"key":"2026011611150954571_j_jisys-2025-0076_ref_003","doi-asserted-by":"crossref","unstructured":"S. Kumano, H. Kera, and T. Yamasaki, \u201cSparse fooling images: fooling machine perception through unrecognizable images,\u201d Pattern Recognit. Lett., vol. 172, no. 8, pp. 259\u2013265, 2023, https:\/\/doi.org\/10.48550\/arXiv.2012.03843.","DOI":"10.1016\/j.patrec.2023.07.003"},{"key":"2026011611150954571_j_jisys-2025-0076_ref_004","doi-asserted-by":"crossref","unstructured":"D. Ding, M. Zhang, F. Feng, Y. Huang, E. Jiang, and M. Yang, \u201cBlack-box adversarial attack on time series classification,\u201d in Proc. AAAI Conf. Artif. Intell., Washington, USA, vol.\u00a037, no. 6, 2023. pp.\u00a07358\u20137368, https:\/\/doi.org\/10.1609\/aaai.v37i6.25896.","DOI":"10.1609\/aaai.v37i6.25896"},{"key":"2026011611150954571_j_jisys-2025-0076_ref_005","doi-asserted-by":"crossref","unstructured":"L. Liu, Z. Xu, D. He, D. Yang, and H. Guo, \u201cLocal pixel attack based on sensitive pixel location for remote sensing images,\u201d Electronics, vol.\u00a012, no. 9, p.\u00a01987, 2023, https:\/\/doi.org\/10.3390\/electronics12091987.","DOI":"10.3390\/electronics12091987"},{"key":"2026011611150954571_j_jisys-2025-0076_ref_006","doi-asserted-by":"crossref","unstructured":"J. Su, D. V. Vargas, and K. Sakurai, \u201cOne pixel attack for fooling deep neural networks,\u201d IEEE Trans. Evol. Comput., vol. 23, no. 5, pp. 828\u2013841, 2019, https:\/\/doi.org\/10.48550\/arXiv.1710.08864.","DOI":"10.1109\/TEVC.2019.2890858"},{"key":"2026011611150954571_j_jisys-2025-0076_ref_007","doi-asserted-by":"crossref","unstructured":"J. Su, D. V. Vargas, and K. Sakurai, \u201cAttacking convolutional neural network using differential evolution,\u201d IPSJ Trans. Comput. Vis. Appl., vol.\u00a011, no. 1, 2019, https:\/\/doi.org\/10.1186\/s41074-019-0053-3.","DOI":"10.1186\/s41074-019-0053-3"},{"key":"2026011611150954571_j_jisys-2025-0076_ref_008","doi-asserted-by":"crossref","unstructured":"Y. Zhou, Y. Tan, Q. Zhang, X. Kuang, Y. Han, and J. Hu, \u201cAn evolutionary-based black-box attack to deep neural network classifiers,\u201d Mob. Networks Appl., vol.\u00a026, no. 4, pp.\u00a01616\u20131629, 2021, https:\/\/doi.org\/10.1007\/s11036-019-01499-x.","DOI":"10.1007\/s11036-019-01499-x"},{"key":"2026011611150954571_j_jisys-2025-0076_ref_009","doi-asserted-by":"crossref","unstructured":"Y. Ge, Z. Yang, L. Chen, Y. Wang, and C. Li, \u201cAttack based on data: A novel perspective to attack sensitive points directly,\u201d Cybersecurity, vol.\u00a06, no. 1, p.\u00a043, 2023, https:\/\/doi.org\/10.1186\/s42400-023-00179-4.","DOI":"10.1186\/s42400-023-00179-4"},{"key":"2026011611150954571_j_jisys-2025-0076_ref_010","unstructured":"I. J. Goodfellow, J. Shlens, and C. Szegedy, \u201cExplaining and harnessing adversarial examples,\u201d in 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, 2015. [Online]. Available: http:\/\/arxiv.org\/abs\/1412.6572."},{"key":"2026011611150954571_j_jisys-2025-0076_ref_011","unstructured":"A. Kurakin, I. J. Goodfellow, and S. Bengio, \u201cAdversarial examples in the physical world,\u201d in 5th International Conf. on Learning Representations, ICLR 2017 - Workshop Track Proc., San Diego, CA, USA, 2019."},{"key":"2026011611150954571_j_jisys-2025-0076_ref_012","unstructured":"A. Madry, A. Makelov, L. Schmidt, D. Tsipras, and A. Vladu, \u201cTowards deep learning models resistant to adversarial attacks,\u201d in 6th Int. Conf. Learn. Represent. ICLR 2018 - Conf, Track Proc., 2018, pp.\u00a01\u201327. [Online]. Available: http:\/\/arxiv.org\/abs\/1706.06083."},{"key":"2026011611150954571_j_jisys-2025-0076_ref_013","doi-asserted-by":"crossref","unstructured":"N. Papernot, P. McDaniel, X. Wu, S. Jha, and A. Swami, \u201cDistillation as a defense to adversarial perturbations against deep neural networks,\u201d in Proc. - 2016 IEEE Symposium on Security and Privacy, SP 2016, San Jose, CA, USA, 2016, pp.\u00a0582\u2013597.","DOI":"10.1109\/SP.2016.41"},{"key":"2026011611150954571_j_jisys-2025-0076_ref_014","unstructured":"S. Cheng, Y. Dong, T. Pang, H. Su, and J. Zhu, \u201cImproving black-box adversarial attacks with a transfer-based prior,\u201d Adv. Neural Inf. Process. Syst., vol.\u00a032, 2019, https:\/\/doi.org\/10.48550\/arXiv.1906.06919."},{"key":"2026011611150954571_j_jisys-2025-0076_ref_015","doi-asserted-by":"crossref","unstructured":"C. Li, H. Wang, J. Zhang, W. Yao, and T. Jiang, \u201cAn approximated gradient sign method using differential evolution for black-box adversarial attack,\u201d IEEE Trans. Evol. Comput., vol.\u00a026, no. 5, pp.\u00a0976\u2013990, 2022, https:\/\/doi.org\/10.1109\/TEVC.2022.3151373.","DOI":"10.1109\/TEVC.2022.3151373"},{"key":"2026011611150954571_j_jisys-2025-0076_ref_016","doi-asserted-by":"crossref","unstructured":"C. Li, T. Jiang, H. Wang, W. Yao, and D. Wang, \u201cOptimizing latent variables in integrating transfer and query based attack framework,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol. 47, no. 1, pp. 161\u2013171, 2024, https:\/\/doi.org\/10.1109\/TPAMI.2024.3461686.","DOI":"10.1109\/TPAMI.2024.3461686"},{"key":"2026011611150954571_j_jisys-2025-0076_ref_017","unstructured":"J. Li, X. Liu, J. Zhao, and F. Shen, \u201cAutoAdversary: a pixel pruning method for sparse adversarial attack,\u201d arXiv Prepr., no. 1, 2022, https:\/\/doi.org\/10.48550\/arXiv.2203.09756."},{"key":"2026011611150954571_j_jisys-2025-0076_ref_018","doi-asserted-by":"crossref","unstructured":"W. Yang, J. Yuan, X. Wang, and P. Zhao, \u201cTSadv: Black-box adversarial attack on time series with local perturbations,\u201d Eng. Appl. Artif. Intell. Int. J.\u00a0Intell. Real-Time Autom, vol. 37, no. 6, pp. 7358\u20137368, 2022, https:\/\/doi.org\/10.1016\/j.engappai.2022.105218.","DOI":"10.1016\/j.engappai.2022.105218"},{"key":"2026011611150954571_j_jisys-2025-0076_ref_019","doi-asserted-by":"crossref","unstructured":"F. T. Liu, K. M. Ting, and Z. H. Zhou, \u201cIsolation-based anomaly detection,\u201d ACM Trans. Knowl. Discov. Data, vol.\u00a06, no. 1, p.\u00a03, 2012, https:\/\/doi.org\/10.1145\/2133360.2133363.","DOI":"10.1145\/2133360.2133363"},{"key":"2026011611150954571_j_jisys-2025-0076_ref_020","doi-asserted-by":"crossref","unstructured":"R. Geirhos et al.., \u201cShortcut learning in deep neural networks,\u201d Nat. Mach. Intell., vol.\u00a02, no. 11, pp.\u00a0665\u2013673, 2020, https:\/\/doi.org\/10.1038\/s42256-020-00257-z.","DOI":"10.1038\/s42256-020-00257-z"},{"key":"2026011611150954571_j_jisys-2025-0076_ref_021","unstructured":"G. Hinton, O. Vinyals, and J. Dean, \u201cDistilling the knowledge in a neural network,\u201d Comput. Sci., vol.\u00a014, no. 7, pp.\u00a038\u201339, 2015, https:\/\/doi.org\/10.48550\/arXiv.1503.02531."},{"key":"2026011611150954571_j_jisys-2025-0076_ref_022","unstructured":"H. Xiao, K. Rasul, and R. Vollgraf, \u201cFashion-mnist: A novel image dataset for benchmarking machine learning algorithms,\u201d arXiv Prepr, no. 1, 2017, https:\/\/doi.org\/10.48550\/arXiv.1708.07747."},{"key":"2026011611150954571_j_jisys-2025-0076_ref_023","unstructured":"M. Lin, Q. Chen, and S. Yan, \u201cNetwork in network,\u201d arXiv Prepr, no. 1, 2013, https:\/\/doi.org\/10.48550\/arXiv.1312.4400."},{"key":"2026011611150954571_j_jisys-2025-0076_ref_024","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., Las Vegas, NV, USA, vols. 2016-Decem, pp.\u00a0770\u2013778, 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2026011611150954571_j_jisys-2025-0076_ref_025","doi-asserted-by":"crossref","unstructured":"J. Kennedy and R. Eberhart, \u201cParticle swarm optimization,\u201d in Proc. of ICNN\u201995-international Conf. on Neural Networks, Perth, WA, Australia, vol.\u00a04, 1995, pp.\u00a01942\u20131948.","DOI":"10.1109\/ICNN.1995.488968"}],"container-title":["Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/jisys-2025-0076\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/jisys-2025-0076\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T11:15:31Z","timestamp":1768562131000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/jisys-2025-0076\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,1]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,15]]},"published-print":{"date-parts":[[2026,1,23]]}},"alternative-id":["10.1515\/jisys-2025-0076"],"URL":"https:\/\/doi.org\/10.1515\/jisys-2025-0076","relation":{},"ISSN":["2191-026X"],"issn-type":[{"value":"2191-026X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,1]]},"article-number":"20250076"}}