{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T05:57:15Z","timestamp":1767333435806,"version":"3.48.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["25KJ2207"],"award-info":[{"award-number":["25KJ2207"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["23K11174"],"award-info":[{"award-number":["23K11174"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Japan Science and Technology Agency (JST) Support for Pioneering Research Initiated by the Next Generation","award":["JPMJSP2129"],"award-info":[{"award-number":["JPMJSP2129"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3648201","type":"journal-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T18:46:53Z","timestamp":1766602013000},"page":"217504-217518","source":"Crossref","is-referenced-by-count":0,"title":["IFAP: Input-Frequency Adaptive Adversarial Perturbation via Full-Spectrum Envelope Constraint for Spectral Fidelity"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5586-0425","authenticated-orcid":false,"given":"Masatomo","family":"Yoshida","sequence":"first","affiliation":[{"name":"Graduate School of Science and Engineering, Doshisha University, Kyoto, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3245-2672","authenticated-orcid":false,"given":"Masahiro","family":"Okuda","sequence":"additional","affiliation":[{"name":"Graduate School of Science and Engineering, Doshisha University, Kyoto, Japan"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/CVPR52688.2022.01167"},{"volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","key":"ref3"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.21037\/qims-24-1400"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1038\/s41598-024-81752-w"},{"volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Szegedy","article-title":"Intriguing properties of neural networks","key":"ref6"},{"volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Goodfellow","article-title":"Explaining and harnessing adversarial examples","key":"ref7"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.48550\/ARXIV.1706.06083"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/CVPRW.2018.00211"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/QoMEX.2019.8743213"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/CVPRW.2018.00212"},{"key":"ref12","first-page":"1","article-title":"Low frequency adversarial perturbation","volume-title":"Proc. Conf. Uncertainty Artif. Intell. (UAI)","author":"Guo"},{"key":"ref13","article-title":"Measuring the tendency of CNNs to learn surface statistical regularities","author":"Jo","year":"2017","journal-title":"arXiv:1711.11561"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.24963\/ijcai.2021\/304"},{"key":"ref15","first-page":"13276","article-title":"A Fourier perspective on model robustness in computer vision","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Yin"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1038\/s42256-020-00257-z"},{"volume-title":"Proc. NeurIPS Workshop Distribution Shifts, Connecting Methods Appl.","author":"Wang","article-title":"Frequency shortcut learning in neural networks","key":"ref17"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/CVPR52733.2024.00281"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/CVPR42600.2020.00871"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.24963\/ijcai.2019\/470"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/WACV45572.2020.9093429"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1007\/978-3-030-68238-5_36"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/TIP.2022.3202366"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1201\/9781351251389-8"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/CVPR.2016.282"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/SP.2017.49"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/EuroSP.2016.36"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/CVPR.2018.00957"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/CVPR.2019.00284"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/ICASSP43922.2022.9746949"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/ACCESS.2024.3415356"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1109\/IMIP57114.2023.00019"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1561\/116.00000113"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.3390\/signals5040040"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1016\/j.patcog.2023.110018"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/GCCE56475.2022.10014404"},{"volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Geirhos","article-title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","key":"ref37"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/CVPR.2017.17"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/CVPR.2018.00465"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1109\/TIP.2013.2251645"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.1109\/CVPR.2018.00068"},{"volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Laidlaw","article-title":"Perceptual adversarial robustness: Defense against unseen threat models","key":"ref42"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1109\/ICCP51581.2021.9466271"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1016\/j.asoc.2025.113466"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1109\/TII.2024.3366993"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1109\/CVPRW53098.2021.00096"},{"key":"ref47","article-title":"Understanding layer-wise contributions in deep neural networks through spectral analysis","author":"Dandi","year":"2021","journal-title":"arXiv:2111.03972"},{"key":"ref48","first-page":"5301","article-title":"On the spectral bias of neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Rahaman"},{"key":"ref49","article-title":"Frequency principle: Fourier analysis sheds light on deep neural networks","author":"John Xu","year":"2019","journal-title":"arXiv:1901.06523"},{"doi-asserted-by":"publisher","key":"ref50","DOI":"10.1609\/aaai.v35i12.17261"},{"doi-asserted-by":"publisher","key":"ref51","DOI":"10.1109\/ICCV48922.2021.00051"},{"key":"ref52","first-page":"9573","article-title":"The pitfalls of simplicity bias in neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Shah"},{"key":"ref53","first-page":"1256","article-title":"Gradient starvation: A learning proclivity in neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Pezeshki"},{"doi-asserted-by":"publisher","key":"ref54","DOI":"10.1038\/s41467-019-08987-4"},{"doi-asserted-by":"publisher","key":"ref55","DOI":"10.1109\/ICCV51070.2023.00138"},{"doi-asserted-by":"publisher","key":"ref56","DOI":"10.1109\/CVPR52734.2025.02346"},{"doi-asserted-by":"publisher","key":"ref57","DOI":"10.1007\/978-3-030-01264-9_28"},{"doi-asserted-by":"publisher","key":"ref58","DOI":"10.1109\/CVPR.2019.00014"},{"volume-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref59"},{"key":"ref60","first-page":"7","article-title":"Reading digits in natural images with unsupervised feature learning","volume-title":"Proc. NIPS workshop deep Learn. unsupervised feature Learn.","author":"Netzer"},{"doi-asserted-by":"publisher","key":"ref61","DOI":"10.1109\/5.726791"},{"key":"ref62","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"doi-asserted-by":"publisher","key":"ref63","DOI":"10.1109\/CVPR.2014.461"},{"doi-asserted-by":"publisher","key":"ref64","DOI":"10.1109\/CVPR.2017.734"},{"doi-asserted-by":"publisher","key":"ref65","DOI":"10.1109\/CVPR.2015.7298970"},{"key":"ref66","first-page":"1","article-title":"Improving native CNN robustness with filter frequency regularization","volume":"2023","author":"Lukasik","year":"2023","journal-title":"Trans. Mach. Learn. Res. (TMLR)"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11314522.pdf?arnumber=11314522","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T05:52:25Z","timestamp":1767333145000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11314522\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3648201","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}