{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T08:07:50Z","timestamp":1779437270135,"version":"3.53.1"},"reference-count":71,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T00:00:00Z","timestamp":1775779200000},"content-version":"vor","delay-in-days":40,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001652","name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001652","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["K\u00fcnstl Intell"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Smart Grids (SG) enhance efficiency and centralised control by enabling networked device communication, but these capabilities expose them to cyberattacks. Machine Learning (ML) and Deep Learning (DL) based Intrusion Detection Systems (IDS) have been employed to detect these threats. Yet, their adoption introduces new adversarial risks: specifically, attacks designed to fool IDS into misclassifying malicious activity as benign. In this study, we propose ADVIS-G, a novel, adversarially defended IDS framework for smart grids utilising deep learning. Our approach begins by training a high-accuracy (macro F1 96+%) classifier on session images from a DNP3-related dataset. We then assess vulnerability to adversarial examples generated using Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), and Momentum Iterative Method (MIM) under varying perturbation rates. To counter such attacks, we introduce an adversarial blocking model based on autoencoder architectures that reconstruct input images, effectively removing adversarial perturbations. Experimental evaluation shows that under MIM, while the baseline model\u2019s macro F1 drops to\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\sim $$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    0.5 (at\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\epsilon $$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    =0.1), adversarial training improves robustness to 0.7. Our proposed autoencoder-based blocking further increases the F1-score to\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\sim $$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    0.92 with RDU-Net, and\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\sim $$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    0.9 with U-Net. But the U-Net performed comparatively better under heavier attacks and normal images. Moreover, combining adversarial training with autoencoder defence achieves the highest resilience under stronger attacks. Additionally, MAE thresholding on reconstructions enables adversarial detection with an Area Under Curve (AUC) of 0.914 using RDU-Net and of 0.865 using U-Net. These results suggest that ADVIS-G significantly enhances IDS robustness against adversarial attacks, offering a promising direction for future smart grid security research.\n                  <\/jats:p>","DOI":"10.1007\/s13218-026-00905-3","type":"journal-article","created":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T08:50:06Z","timestamp":1775811006000},"page":"55-77","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ADVIS-G: An Adversarially Defended Intrusion Detection System for Smart Grids Using Deep Learning"],"prefix":"10.1007","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5268-4380","authenticated-orcid":false,"given":"Ramkrishna","family":"Acharya","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8461-5154","authenticated-orcid":false,"given":"Loui","family":"Al Sardy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9685-8880","authenticated-orcid":false,"given":"Mamdouh","family":"Muhammad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9071-4802","authenticated-orcid":false,"given":"Reinhard","family":"German","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,10]]},"reference":[{"key":"905_CR1","unstructured":"U.S. Department of Energy, Office of Electricity Delivery and Energy Reliability. The Smart Grid: An Introduction. U.S. Department of Energy, 2008. Available at: https:\/\/www.energy.gov\/oe\/smart-grid-primer-smart-grid-books"},{"key":"905_CR2","doi-asserted-by":"publisher","unstructured":"Olufemi A (2021) Omitaomu and Haoran Niu. Artificial intelligence techniques in smart grid: A survey. Smart Cities, 4(2):548\u2013568, Available at: https:\/\/doi.org\/10.3390\/smartcities4020029","DOI":"10.3390\/smartcities4020029"},{"key":"905_CR3","doi-asserted-by":"publisher","unstructured":"Achaal B, Adda M, Berger M, Ibrahim H, Awde A (2024) Study of smart grid cyber-security, examining architectures, communication networks, cyber-attacks, countermeasure techniques, and challenges. Cybersecurity, 7(1):10, Available at: https:\/\/doi.org\/10.1186\/s42400-023-00200-w","DOI":"10.1186\/s42400-023-00200-w"},{"key":"905_CR4","doi-asserted-by":"publisher","unstructured":"David\u00a0E (2017) Whitehead, Kevin Owens, Dennis Gammel, and Jess Smith. Ukraine cyber-induced power outage: Analysis and practical mitigation strategies. In: 2017 70th Annual Conference for Protective Relay Engineers (CPRE), pages 1\u20138, Available at: https:\/\/doi.org\/10.1109\/CPRE.2017.8090056","DOI":"10.1109\/CPRE.2017.8090056"},{"key":"905_CR5","unstructured":"CPO Magazine (2021) Colorado energy company suffered a cyber attack destroying 25 years of data and shut down internal controls. Available at: https:\/\/bit.ly\/cpomagazine"},{"key":"905_CR6","doi-asserted-by":"publisher","unstructured":"Barbieri G, Conti M, Tippenhauer NO, Turrin F (, ) Assessing the use of insecure ICS protocols via IXP network traffic analysis. In: 2021 International Conference on Computer Communications and Networks (ICCCN), p 1\u20139. Available at: https:\/\/doi.org\/10.1109\/ICCCN52240.2021.9522219","DOI":"10.1109\/ICCCN52240.2021.9522219"},{"key":"905_CR7","doi-asserted-by":"publisher","unstructured":"Khan I, Farrukh Y\u00a0A, Wali S (2024) Bytestack-id: Integrated stacked model leveraging payload byte frequency for grayscale image-based network intrusion detection. In: ICC 2024 - IEEE International Conference on Communications, p 2731\u20132736, Available at: https:\/\/doi.org\/10.1109\/ICC51166.2024.10622596","DOI":"10.1109\/ICC51166.2024.10622596"},{"key":"905_CR8","doi-asserted-by":"publisher","unstructured":"Zhou L, Ouyang X, Ying H, Han L, Cheng Y, Zhang T (2018) Cyber-attack classification in smart grid via deep neural network. In: Proceedings of the 2nd International Conference on Computer Science and Application Engineering, CSAE \u201918, New York, NY, USA, Association for Computing Machinery. Available at: https:\/\/doi.org\/10.1145\/3207677.3278054","DOI":"10.1145\/3207677.3278054"},{"key":"905_CR9","doi-asserted-by":"publisher","unstructured":"Ibitoye O, Abou-Khamis R, ElShehaby M, Matrawy A, Shafiq M (2025) The threat of adversarial attacks against machine learning in network security: A survey. J Electr Eng, 01. Available at: https:\/\/doi.org\/10.37256\/jeee.4120255738","DOI":"10.37256\/jeee.4120255738"},{"key":"905_CR10","doi-asserted-by":"publisher","unstructured":"IEEE. Ieee standard for electric power systems communications-distributed network protocol (dnp3). IEEE Std 1815-2012 (Revision of IEEE Std 1815-2010), pages 1\u2013821, 2012. Available at: https:\/\/doi.org\/10.1109\/IEEESTD.2012.6327578","DOI":"10.1109\/IEEESTD.2012.6327578"},{"key":"905_CR11","unstructured":"Newton-Evans Research Company, Inc. 94% of north american electric utilities surveyed use dnp3 for scada, 2019. Available at: https:\/\/www.newton-evans.com\/94-of-north-american-electric-utilities-surveyed-use-dnp3-for-scada\/"},{"key":"905_CR12","unstructured":"Rosborough C, Gordon C, Waldron B (2019) All about eve: Comparing dnp3 secure authentication with standard security technologies for scada communications. Technical report, Schweitzer Engineering Laboratories, Inc., November . Available at: https:\/\/selinc.com\/api\/download\/125641\/"},{"key":"905_CR13","doi-asserted-by":"publisher","unstructured":"Kelli V, Radoglou-Grammatikis P, Sesis A (2022) Thomas Lagkas, Eleftherios Fountoukidis, Emmanouil Kafetzakis, Ioannis Giannoulakis, and Panagiotis Sarigiannidis. Attacking and defending dnp3 ics\/scada systems. In: 2022 18th International Conference on Distributed Computing in Sensor Systems (DCOSS), p 183\u2013190. IEEE . Available at: https:\/\/doi.org\/10.1109\/DCOSS54816.2022.00041","DOI":"10.1109\/DCOSS54816.2022.00041"},{"key":"905_CR14","doi-asserted-by":"publisher","unstructured":"Hu Y, Yang A, Li H, Sun Y, Sun LA (2018) survey of intrusion detection on industrial control systems. Int J Distrib Sens Netw, 14(8):1550147718794615, Available at: https:\/\/doi.org\/10.1177\/1550147718794615","DOI":"10.1177\/1550147718794615"},{"issue":"1","key":"905_CR15","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1109\/COMST.2016.2616442","volume":"19","author":"S Tan","year":"2017","unstructured":"Tan S, De D, Song W-Z, Yang J, Das SK (2017) Survey of security advances in smart grid: A data driven approach. IEEE Commun Surv Tutor 19(1):397\u2013422","journal-title":"IEEE Commun Surv Tutor"},{"key":"905_CR16","doi-asserted-by":"publisher","first-page":"6048087","DOI":"10.1155\/2023\/6048087","volume":"1","author":"A Momand","year":"2023","unstructured":"Momand A, Jan SU (2023) A systematic and comprehensive survey of recent advances in intrusion detection systems using machine learning: Deep learning, datasets, and attack taxonomy. J Sens 1:6048087","journal-title":"J Sens"},{"key":"905_CR17","doi-asserted-by":"publisher","unstructured":"Sahani N, Zhu R, Cho J-H, Liu C-C (2023) Machine learning-based intrusion detection for smart grid computing: A survey. 7(2), April . Available at: https:\/\/doi.org\/10.1145\/3578366","DOI":"10.1145\/3578366"},{"key":"905_CR18","unstructured":"Jacobson V, Floyd S, Paxson V, McCanne S (1988) tcpdump. Lawrence Berkeley National Laboratory . Available at: https:\/\/www.tcpdump.org\/"},{"key":"905_CR19","doi-asserted-by":"publisher","unstructured":"Moreira R, Rodrigues L\u00a0F, Rosa P\u00a0F, Aguiar RL, de\u00a0Oliveira Silva F (2020) Packet vision: a convolutional neural network approach for network traffic classification. In: 2020 33rd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), p 256\u2013263 . Available at: https:\/\/doi.org\/10.1109\/SIBGRAPI51738.2020.00042","DOI":"10.1109\/SIBGRAPI51738.2020.00042"},{"key":"905_CR20","unstructured":"Iandola F\u00a0N., Han S, Moskewicz M\u00a0W, Ashraf K, Dally W\u00a0J, Keutzer K (2016) Squeezenet: Alexnet-level accuracy with 50x fewer parameters and $$<$$0.5mb model size. arXiv:1602.07360,"},{"key":"905_CR21","doi-asserted-by":"publisher","unstructured":"Krizhevsky A, Sutskever I, Hinton G\u00a0E (2017) Imagenet classification with deep convolutional neural networks. Commun ACM, 60(6):84\u201390, May . Available at: https:\/\/doi.org\/10.1145\/3065386","DOI":"10.1145\/3065386"},{"key":"905_CR22","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), p 770\u2013778, . Available at: https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"905_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2021.108117","volume":"194","author":"L Yu","year":"2021","unstructured":"Yu L, Dong J, Chen L, Li M, Xu B, Li Z, Qiao L, Liu L, Zhao B, Zhang C (2021) Pbcnn: packet bytes-based convolutional neural network for network intrusion detection. Comput Netw 194:108117","journal-title":"Comput Netw"},{"key":"905_CR24","doi-asserted-by":"publisher","unstructured":"Golubev S, Novikova E, Fedorchenko E (2022) Image-based approach to intrusion detection in cyber-physical objects. Information, 13(12). Available at: https:\/\/doi.org\/10.3390\/info13120553","DOI":"10.3390\/info13120553"},{"key":"905_CR25","doi-asserted-by":"publisher","unstructured":"Goh J, Adepu S, Junejo K\u00a0N, Mathur A (2017) A dataset to support research in the design of secure water treatment systems. In: Grigore Havarneanu, Roberto Setola, Hypatia Nassopoulos, and Stephen Wolthusen, editors, Critical Information Infrastructures Security, p 88\u201399, Cham. Springer International Publishing. Available at: https:\/\/doi.org\/10.1007\/978-3-319-71368-7_8","DOI":"10.1007\/978-3-319-71368-7_8"},{"key":"905_CR26","doi-asserted-by":"publisher","unstructured":"Altunay H\u00a0C, Albayrak Z (2023) A hybrid cnn+lstm-based intrusion detection system for industrial iot networks. Eng Sci Technol Int J, 38:101322, Available at:https:\/\/doi.org\/10.1016\/j.jestch.2022.101322","DOI":"10.1016\/j.jestch.2022.101322"},{"key":"905_CR27","doi-asserted-by":"publisher","unstructured":"Moustafa N, Slay J (2015) UNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set). In: 2015 Military Communications and Information Systems Conference (MilCIS), p 1\u20136, Canberra, ACT, Australia, Available at: https:\/\/doi.org\/10.1109\/MilCIS.2015.7348942","DOI":"10.1109\/MilCIS.2015.7348942"},{"key":"905_CR28","doi-asserted-by":"publisher","unstructured":"Al-Hawawreh M, Sitnikova E, Aboutorab N (2022) X-iiotid: A connectivity-agnostic and device-agnostic intrusion data set for industrial internet of things. IEEE Internet of Things Journal, 9(5):3962\u20133977. Available at: https:\/\/doi.org\/10.1109\/JIOT.2021.3102056","DOI":"10.1109\/JIOT.2021.3102056"},{"issue":"3","key":"905_CR29","first-page":"1","volume":"15","author":"A Alsaiari","year":"2024","unstructured":"Alsaiari A, Ilyas M (2024) Deep learning for smart grid intrusion detection: A hybrid CNN-LSTM-based model. Int J Artif Intell Appl 15(3):1\u201314","journal-title":"Int J Artif Intell Appl"},{"key":"905_CR30","doi-asserted-by":"crossref","unstructured":"Baalia S, Boughareb D, Kouahla Z, Seridi H (2025) Enhanced intrusion detection in smart grids using extended long short-term memory variants. Int J Adv Intell Inf, 11(4),","DOI":"10.26555\/ijain.v11i4.2169"},{"key":"905_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2022.109073","volume":"214","author":"H Jmila","year":"2022","unstructured":"Jmila H, Khedher MI (2022) Adversarial machine learning for network intrusion detection: A comparative study. Comput Netw 214:109073","journal-title":"Comput Netw"},{"key":"905_CR32","doi-asserted-by":"publisher","unstructured":"Tavallaee M, Ebrahim B, Wei L, and Ali\u00a0A (2009) A detailed analysis of the kdd cup 99 data set. In: 2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications, p 1\u20136 . Available at: https:\/\/doi.org\/10.1109\/CISDA.2009.5356528","DOI":"10.1109\/CISDA.2009.5356528"},{"key":"905_CR33","doi-asserted-by":"publisher","unstructured":"Alotaibi A, Rassam M (2023) Adversarial machine learning attacks against intrusion detection systems: A survey on strategies and defense. Future Internet, 15:62, 01. Available at: https:\/\/doi.org\/10.3390\/fi15020062","DOI":"10.3390\/fi15020062"},{"key":"905_CR34","unstructured":"Alatwi H\u00a0A, Morisset C (2021) Adversarial machine learning in network intrusion detection domain: A systematic review, Available at: https:\/\/arxiv.org\/abs\/2112.03315"},{"key":"905_CR35","doi-asserted-by":"crossref","unstructured":"Hao J, Tao Y (2022) Adversarial attacks on deep learning models in smart grids. In: 2021 6th International Conference on Clean Energy and Power Generation Technology Energy Reports, 8:123\u2013129","DOI":"10.1016\/j.egyr.2021.11.026"},{"key":"905_CR36","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.future.2020.04.013","volume":"110","author":"M Pawlicki","year":"2020","unstructured":"Pawlicki M, Chora\u015b M, Kozik R (2020) Defending network intrusion detection systems against adversarial evasion attacks. Futur Gener Comput Syst 110:148\u2013154","journal-title":"Futur Gener Comput Syst"},{"key":"905_CR37","doi-asserted-by":"publisher","unstructured":"Sharafaldin I, Lashkari A\u00a0H, Ghorbani A\u00a0A (2018) Toward generating a new intrusion detection dataset and intrusion traffic characterization. In: Proceedings of the 4th International Conference on Information Systems Security and Privacy (ICISSP), p 108\u2013116. SciTePress, Available at: https:\/\/doi.org\/10.5220\/0006639801080116","DOI":"10.5220\/0006639801080116"},{"key":"905_CR38","volume":"58","author":"E Anthi","year":"2021","unstructured":"Anthi E, Williams L, Rhode M, Burnap P, Wedgbury A (2021) Adversarial attacks on machine learning cybersecurity defences in industrial control systems. J Inf Secur Appl 58:102717","journal-title":"J Inf Secur Appl"},{"key":"905_CR39","doi-asserted-by":"publisher","unstructured":"Sauka K, Shin G-Y, Kim D-W, Han M-M (2022) Adversarial robust and explainable network intrusion detection systems based on deep learning. Appl Sci, 12(13), Available at: https:\/\/doi.org\/10.3390\/app12136451","DOI":"10.3390\/app12136451"},{"key":"905_CR40","doi-asserted-by":"publisher","unstructured":"Asimopoulos D\u00a0C, Radoglou-Grammatikis P, Makris I, Mladenov V, Psannis KE, Goudos S, Sarigiannidis P (2023) Breaching the defense: Investigating fgsm and ctgan adversarial attacks on iec 60870-5-104 ai-enabled intrusion detection systems. In: Proceedings of the 18th International Conference on Availability, Reliability and Security, ARES \u201923, New York, NY, USA . Association for Computing Machinery. Available at: https:\/\/doi.org\/10.1145\/3600160.3605163,","DOI":"10.1145\/3600160.3605163"},{"key":"905_CR41","doi-asserted-by":"publisher","first-page":"157408","DOI":"10.1109\/ACCESS.2024.3473531","volume":"12","author":"GA Sampedro","year":"2024","unstructured":"Sampedro GA, Ojo S, Krichen M, Alamro MA, Mihoub A, Karovic V (2024) Defending ai models against adversarial attacks in smart grids using deep learning. IEEE Access 12:157408\u2013157417","journal-title":"IEEE Access"},{"key":"905_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyai.2024.100381","volume":"17","author":"YM Khaw","year":"2024","unstructured":"Khaw YM, Jahromi AA, Arani MFM, Kundur D (2024) Evasive attacks against autoencoder-based cyberattack detection systems in power systems. Energy and AI 17:100381","journal-title":"Energy and AI"},{"key":"905_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.131357","volume":"656","author":"SM Raza","year":"2025","unstructured":"Raza SM, Abidi SMH, Masuduzzaman M, Shin SY (2025) Lightweight deep learning for visual perception: A survey of models, compression strategies, and edge deployment challenges. Neurocomputing 656:131357","journal-title":"Neurocomputing"},{"issue":"3","key":"905_CR44","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Hao S, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L (2015) ImageNet large scale visual recognition challenge. Int J Comput Vis 115(3):211\u2013252","journal-title":"Int J Comput Vis"},{"key":"905_CR45","unstructured":"TorchVision maintainers and contributors (2016) Torchvision: Pytorch\u2019s computer vision library. https:\/\/github.com\/pytorch\/vision"},{"key":"905_CR46","unstructured":"Wightman R (2019) Pytorch image models. https:\/\/github.com\/rwightman\/pytorch-image-models"},{"key":"905_CR47","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1755","volume":"10","author":"W Zheng","year":"2024","unstructured":"Zheng W, Siyu L, Yang Y, Yin Z, Yin L (2024) Lightweight transformer image feature extraction network. PeerJ Comput Sci 10:e1755","journal-title":"PeerJ Comput Sci"},{"key":"905_CR48","doi-asserted-by":"crossref","unstructured":"Ge T, Chen S-Q, Wei F (2022) Edgeformer: A parameter-efficient transformer for on-device seq2seq generation. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, p 10786\u201310798","DOI":"10.18653\/v1\/2022.emnlp-main.741"},{"key":"905_CR49","doi-asserted-by":"crossref","unstructured":"Tan M, Chen B, Pang R, Vasudevan V, Sandler M, Howard A, Le QV (2019) Mnasnet: Platform-aware neural architecture search for mobile. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, p 2820\u20132828,","DOI":"10.1109\/CVPR.2019.00293"},{"key":"905_CR50","doi-asserted-by":"publisher","unstructured":"Howard A, Sandler M, Chen B, Wang W, Chen L-C, Tan M, Chu G, Vasudevan V, Zhu Y, Pang R, Adam H, Le Q (2019) Searching for mobilenetv3. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), p 1314\u20131324, 2019. Available at: https:\/\/doi.org\/10.1109\/ICCV.2019.00140","DOI":"10.1109\/ICCV.2019.00140"},{"key":"905_CR51","unstructured":"Tan M, Le QV (2020) Efficientnet: Rethinking model scaling for convolutional neural networks"},{"key":"905_CR52","unstructured":"Mehta S, Rastegari M (2021) Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178"},{"key":"905_CR53","first-page":"12934","volume":"35","author":"Y Li","year":"2022","unstructured":"Li Y, Yuan G, Yang Wen JH, Evangelidis G, Tulyakov S, Wang Y, Ren J (2022) Efficientformer: Vision transformers at mobilenet speed. Adv Neural Inf Process Syst 35:12934\u201312949","journal-title":"Adv Neural Inf Process Syst"},{"key":"905_CR54","unstructured":"Yang J, Liao J, Lei F, Liu M, Long L, Chen J, Wan H, Yu B, Zhao W (2023) Tinyformer: Efficient transformer design and deployment on tiny devices. arXiv preprint arXiv:2311.01759"},{"key":"905_CR55","doi-asserted-by":"crossref","unstructured":"Draper-Gil G, Lashkari A\u00a0H, Mamun MSI, Ghorbani AA (2016) Characterization of encrypted and VPN traffic using time-related features. In Proceedings of the 2nd International Conference on Information Systems Security and Privacy - ICISSP, p 407\u2013414. SciTePress","DOI":"10.5220\/0005740704070414"},{"key":"905_CR56","doi-asserted-by":"publisher","first-page":"160397","DOI":"10.1109\/ACCESS.2019.2951526","volume":"7","author":"Y Bakhti","year":"2019","unstructured":"Bakhti Y, Fezza SA, Hamidouche W, D\u00e9forges O (2019) Ddsa: A defense against adversarial attacks using deep denoising sparse autoencoder. IEEE Access 7:160397\u2013160407","journal-title":"IEEE Access"},{"key":"905_CR57","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: Nassir Navab, Joachim Hornegger, William\u00a0M. Wells, and Alejandro\u00a0F. Frangi, editors, Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015, p 234\u2013241, Cham, 2015. Springer International Publishing","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"905_CR58","doi-asserted-by":"publisher","unstructured":"Jia F, Wong W\u00a0H, Zeng T (2021) Ddunet: Dense dense u-net with applications in image denoising. In: 2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW), p 354\u2013364, 2021. Available at: https:\/\/doi.org\/10.1109\/ICCVW54120.2021.00044","DOI":"10.1109\/ICCVW54120.2021.00044"},{"key":"905_CR59","unstructured":"Wilm F, Ammeling J, \u00d6ttl M, Fick R HJ, Aubreville M, Breininger K (2024) Rethinking u-net skip connections for biomedical image segmentation, Available at: https:\/\/arxiv.org\/abs\/2402.08276"},{"key":"905_CR60","unstructured":"Iakubovskii P (2019) Segmentation models pytorch. Available at: https:\/\/github.com\/qubvel\/segmentation_models.pytorch"},{"key":"905_CR61","doi-asserted-by":"publisher","first-page":"31742","DOI":"10.1109\/ACCESS.2021.3061062","volume":"9","author":"J Gurrola-Ramos","year":"2021","unstructured":"Gurrola-Ramos J, Dalmau O, Alarc\u00f3n TE (2021) A residual dense u-net neural network for image denoising. IEEE Access 9:31742\u201331754","journal-title":"IEEE Access"},{"key":"905_CR62","first-page":"2018","volume":"01069","author":"M-I Nicolae","year":"1807","unstructured":"Nicolae M-I, Sinn M, Tran MN, Buesser B, Rawat A, Wistuba M, Zantedeschi V, Baracaldo N, Chen B, Ludwig H, Molloy I, Edwards B (1807) Adversarial robustness toolbox v.12.0. CoRR 01069:2018","journal-title":"CoRR"},{"key":"905_CR63","unstructured":"Goodfellow IJ, Shlens J, Szegedy C, et\u00a0al (2014) Explaining and harnessing adversarial examples (2014). arXiv preprint arXiv:1412.6572"},{"key":"905_CR64","unstructured":"Kurakin A, Goodfellow I, Bengio S (2017) Adversarial machine learning at scale, Available at: https:\/\/arxiv.org\/abs\/1611.01236"},{"key":"905_CR65","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: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, p 9185\u20139193,","DOI":"10.1109\/CVPR.2018.00957"},{"key":"905_CR66","unstructured":"Phan TH, Yamamoto K (2020) Resolving class imbalance in object detection with weighted cross entropy losses. Available at: https:\/\/arxiv.org\/abs\/2006.01413"},{"issue":"4","key":"905_CR67","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\u2013612","journal-title":"IEEE Trans Image Process"},{"key":"905_CR68","doi-asserted-by":"publisher","unstructured":"Zujovic J, Pappas TN, Neuhoff DL (2009) Structural similarity metrics for texture analysis and retrieval. In: 2009 16th IEEE International Conference on Image Processing (ICIP), pages 2225\u20132228. Available at: https:\/\/doi.org\/10.1109\/ICIP.2009.5413897","DOI":"10.1109\/ICIP.2009.5413897"},{"key":"905_CR69","unstructured":"Loshchilov I, Hutter F (2019) Decoupled weight decay regularization . Available at: https:\/\/arxiv.org\/abs\/1711.05101"},{"key":"905_CR70","doi-asserted-by":"crossref","unstructured":"Al-Kababji A, Bensaali F, Dakua S\u00a0P. Scheduling techniques for liver segmentation: Reducelronplateau vs onecyclelr. In: Akram Bennour, Tolga Ensari, Yousri Kessentini, and Sean Eom, editors, Intelligent Systems and Pattern Recognition, p 204\u2013212, Cham, 2022. Springer International Publishing","DOI":"10.1007\/978-3-031-08277-1_17"},{"key":"905_CR71","unstructured":"Simonyan K, Vedaldi A, Zisserman A (2014) Deep inside convolutional networks: Visualising image classification models and saliency maps. Available at: https:\/\/arxiv.org\/abs\/1312.6034"}],"container-title":["KI - K\u00fcnstliche Intelligenz"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13218-026-00905-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13218-026-00905-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13218-026-00905-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T07:50:49Z","timestamp":1779436249000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13218-026-00905-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":71,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["905"],"URL":"https:\/\/doi.org\/10.1007\/s13218-026-00905-3","relation":{},"ISSN":["0933-1875","1610-1987"],"issn-type":[{"value":"0933-1875","type":"print"},{"value":"1610-1987","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"1 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 April 2026","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":"Conflict of interest"}}]}}