{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T20:42:50Z","timestamp":1773002570408,"version":"3.50.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"29","license":[{"start":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T00:00:00Z","timestamp":1721779200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T00:00:00Z","timestamp":1721779200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","award":["PDC2021-121197-C22"],"award-info":[{"award-number":["PDC2021-121197-C22"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100019188","name":"HORIZON EUROPE Excellent Science","doi-asserted-by":"publisher","award":["101120726"],"award-info":[{"award-number":["101120726"]}],"id":[{"id":"10.13039\/100019188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011698","name":"Junta de Comunidades de Castilla-La Mancha","doi-asserted-by":"publisher","award":["SBPLY\/21\/180501\/000025"],"award-info":[{"award-number":["SBPLY\/21\/180501\/000025"]}],"id":[{"id":"10.13039\/501100011698","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2024,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The phenomenon of adversarial examples is one of the most attractive topics in machine learning research these days. These are particular cases that are able to mislead neural networks, with critical consequences. For this reason, different approaches are considered to tackle the problem. On the one side, defense mechanisms, such as AutoEncoder-based methods, are able to learn from the distribution of adversarial perturbations to detect them. On the other side, chaos theory and Lyapunov exponents (LEs) have also been shown to be useful to characterize them. This work proposes the combination of both domains. The proposed method employs these exponents to add more information to the loss function that is used during an AutoEncoder training process. As a result, this method achieves a general improvement in adversarial examples detection performance for a wide variety of attack methods.<\/jats:p>","DOI":"10.1007\/s00521-024-10141-1","type":"journal-article","created":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T02:01:50Z","timestamp":1721786510000},"page":"18265-18275","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Leveraging AutoEncoders and chaos theory to improve adversarial example detection"],"prefix":"10.1007","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7748-6756","authenticated-orcid":false,"given":"Anibal","family":"Pedraza","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0841-4131","authenticated-orcid":false,"given":"Oscar","family":"Deniz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9713-6048","authenticated-orcid":false,"given":"Harbinder","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7345-4869","authenticated-orcid":false,"given":"Gloria","family":"Bueno","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,7,24]]},"reference":[{"key":"10141_CR1","unstructured":"Goodfellow IJ, Shlens J, Szegedy C (2015) Explaining and harnessing adversarial examples. In: International conference on learning representations (ICLR)"},{"issue":"12","key":"10141_CR2","doi-asserted-by":"publisher","first-page":"1821","DOI":"10.1007\/s10483-022-2917-7","volume":"43","author":"C Li","year":"2022","unstructured":"Li C, Zhu C, Lim C et al (2022) Nonlinear in-plane thermal buckling of rotationally restrained functionally graded carbon nanotube reinforced composite shallow arches under uniform radial loading. Appl Math Mech 43(12):1821\u20131840","journal-title":"Appl Math Mech"},{"issue":"9","key":"10141_CR3","first-page":"24501037","volume":"24","author":"H Li","year":"2023","unstructured":"Li H, Wang W, Lai S et al (2023) Nonlinear vibration and stability analysis of rotating functionally graded piezoelectric nanobeams. Int J Struct Stabil Dyn 24(9):24501037","journal-title":"Int J Struct Stabil Dyn"},{"key":"10141_CR4","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1016\/j.compeleceng.2017.04.009","volume":"63","author":"YD Zhang","year":"2017","unstructured":"Zhang YD, Zhang Y, Lv YD et al (2017) Alcoholism detection by medical robots based on hu moment invariants and predator-prey adaptive-inertia chaotic particle swarm optimization. Comput Electr Eng 63:126\u2013138","journal-title":"Comput Electr Eng"},{"issue":"9","key":"10141_CR5","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1177\/0037549716667834","volume":"92","author":"Y Zhang","year":"2016","unstructured":"Zhang Y, Wu X, Lu S et al (2016) Smart detection on abnormal breasts in digital mammography based on contrast-limited adaptive histogram equalization and chaotic adaptive real-coded biogeography-based optimization. Simulation 92(9):873\u2013885","journal-title":"Simulation"},{"key":"10141_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.aeue.2020.153424","volume":"127","author":"M Samimi","year":"2020","unstructured":"Samimi M, Majidi MH, Khorashadizadeh S (2020) Secure communication based on chaos synchronization using brain emotional learning. AEU-Int J Electron Commun 127:153424","journal-title":"AEU-Int J Electron Commun"},{"issue":"8","key":"10141_CR7","doi-asserted-by":"publisher","first-page":"6521","DOI":"10.1007\/s00521-021-06768-z","volume":"34","author":"F Aliabadi","year":"2022","unstructured":"Aliabadi F, Majidi MH, Khorashadizadeh S (2022) Chaos synchronization using adaptive quantum neural networks and its application in secure communication and cryptography. Neural Comput Appl 34(8):6521\u20136533","journal-title":"Neural Comput Appl"},{"key":"10141_CR8","unstructured":"Madry A, Makelov A, Schmidt L, et al (2018) Towards deep learning models resistant to adversarial attacks. In: International conference on learning representations (ICLR)"},{"key":"10141_CR9","doi-asserted-by":"crossref","unstructured":"Moosavi-Dezfooli SM, Fawzi A, Frossard P (2016) Deepfool: a simple and accurate method to fool deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2574\u20132582","DOI":"10.1109\/CVPR.2016.282"},{"key":"10141_CR10","doi-asserted-by":"crossref","unstructured":"Chen PY, Sharma Y, Zhang H, et al (2018) EAD: elastic-net attacks to deep neural networks via adversarial examples. In: Thirty-second AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.11302"},{"key":"10141_CR11","doi-asserted-by":"crossref","unstructured":"Moosavi-Dezfooli SM, Fawzi A, Fawzi O, et al (2017) Universal adversarial perturbations. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1765\u20131773","DOI":"10.1109\/CVPR.2017.17"},{"key":"10141_CR12","doi-asserted-by":"crossref","unstructured":"Papernot N, McDaniel P, Wu X, et al (2016) Distillation as a defense to adversarial perturbations against deep neural networks. In: 2016 IEEE symposium on security and privacy (SP), IEEE, pp 582\u2013597","DOI":"10.1109\/SP.2016.41"},{"key":"10141_CR13","doi-asserted-by":"crossref","unstructured":"Carlini N, Wagner D (2017) Towards evaluating the robustness of neural networks. In: 2017 IEEE symposium on security and privacy (sp), IEEE, pp 39\u201357","DOI":"10.1109\/SP.2017.49"},{"key":"10141_CR14","unstructured":"Brendel W, Rauber J, Bethge M (2017) Decision-based adversarial attacks: reliable attacks against black-box machine learning models. arXiv preprint arXiv:1712.04248"},{"key":"10141_CR15","doi-asserted-by":"crossref","unstructured":"Chen J, Jordan MI, Wainwright MJ (2020) HopSkipJumpAttack: a query-efficient decision-based attack. In: 2020 IEEE symposium on security and privacy (sp), IEEE, pp 1277\u20131294","DOI":"10.1109\/SP40000.2020.00045"},{"key":"10141_CR16","doi-asserted-by":"crossref","unstructured":"Papernot N, McDaniel P, Wu X, et al (2016) Distillation as a defense to adversarial perturbations against deep neural networks. In: 2016 IEEE symposium on security and privacy (SP), pp 582\u2013597","DOI":"10.1109\/SP.2016.41"},{"key":"10141_CR17","doi-asserted-by":"crossref","unstructured":"Wang C, Tindemans S, Pan K, et al (2020) Detection of false data injection attacks using the autoencoder approach. In: 2020 international conference on probabilistic methods applied to power systems (PMAPS), pp 1\u20136","DOI":"10.1109\/PMAPS47429.2020.9183526"},{"key":"10141_CR18","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1007\/978-3-031-06791-4_19","volume-title":"Artif Intell Secur","author":"H Ye","year":"2022","unstructured":"Ye H, Liu X, Yan A et al (2022) Detect adversarial examples by using feature autoencoder. In: Sun X, Zhang X, Xia Z et al (eds) Artif Intell Secur. Springer International Publishing, Cham, pp 233\u2013242"},{"issue":"9","key":"10141_CR19","doi-asserted-by":"publisher","first-page":"1523","DOI":"10.1109\/JAS.2021.1004108","volume":"8","author":"H Samuel","year":"2021","unstructured":"Samuel H, Fazle K, Houshang D (2021) Generating adversarial samples on multivariate time series using variational autoencoders. IEEE\/CAA J Autom Sin 8(9):1523\u20131538","journal-title":"IEEE\/CAA J Autom Sin"},{"key":"10141_CR20","doi-asserted-by":"crossref","unstructured":"Cintas C, Speakman S, Akinwande V, et al (2021) Detecting adversarial attacks via subset scanning of autoencoder activations and reconstruction error. In: Proceedings of the twenty-ninth international conference on international joint conferences on artificial intelligence, pp 876\u2013882","DOI":"10.24963\/ijcai.2020\/122"},{"key":"10141_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2022.102640","volume":"116","author":"M Hassanin","year":"2022","unstructured":"Hassanin M, Moustafa N, Tahtali M et al (2022) Rethinking maximum-margin softmax for adversarial robustness. Comput Secur 116:102640","journal-title":"Comput Secur"},{"key":"10141_CR22","doi-asserted-by":"crossref","unstructured":"Zhuo Y, Song Z, Ge Z (2023) Security versus accuracy: trade-off data modeling to safe fault classification systems. IEEE Trans Neural Netw Learn Syst","DOI":"10.1109\/TNNLS.2023.3251999"},{"key":"10141_CR23","doi-asserted-by":"crossref","unstructured":"Harder P, Pfreundt FJ, Keuper M, et al (2021) Spectraldefense: detecting adversarial attacks on cnns in the fourier domain. In: 2021 international joint conference on neural networks (IJCNN), IEEE, pp 1\u20138","DOI":"10.1109\/IJCNN52387.2021.9533442"},{"key":"10141_CR24","doi-asserted-by":"publisher","first-page":"1711","DOI":"10.1109\/TIP.2019.2940533","volume":"29","author":"A Mustafa","year":"2020","unstructured":"Mustafa A, Khan SH, Hayat M et al (2020) Image super-resolution as a defense against adversarial attacks. IEEE Trans Image Process 29:1711\u20131724","journal-title":"IEEE Trans Image Process"},{"key":"10141_CR25","doi-asserted-by":"crossref","unstructured":"Yan H, Zhang J, Feng J, et al (2022) Towards adversarially robust deep image denoising","DOI":"10.24963\/ijcai.2022\/211"},{"issue":"10","key":"10141_CR26","doi-asserted-by":"publisher","first-page":"1304","DOI":"10.3390\/e23101304","volume":"23","author":"M Pawlicki","year":"2021","unstructured":"Pawlicki M, Chora\u015b RS (2021) Preprocessing pipelines including block-matching convolutional neural network for image denoising to robustify deep reidentification against evasion attacks. Entropy 23(10):1304","journal-title":"Entropy"},{"key":"10141_CR27","unstructured":"Prabhu VU, Desai N, Whaley J (2017) On Lyapunov exponents and adversarial perturbation. Deep Learning Security Workshop (Singapore)"},{"issue":"11","key":"10141_CR28","doi-asserted-by":"publisher","first-page":"1201","DOI":"10.3390\/e22111201","volume":"22","author":"A Pedraza","year":"2020","unstructured":"Pedraza A, Deniz O, Bueno G (2020) Approaching adversarial example classification with chaos theory. Entropy 22(11):1201","journal-title":"Entropy"},{"key":"10141_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2021.111745","volume":"155","author":"A Pedraza","year":"2022","unstructured":"Pedraza A, Deniz O, Bueno G (2022) Lyapunov stability for detecting adversarial image examples. Chaos Solitons Fract 155:111745","journal-title":"Chaos Solitons Fract"},{"key":"10141_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2022.112577","volume":"163","author":"O Deniz","year":"2022","unstructured":"Deniz O, Pedraza A, Bueno G (2022) Detecting chaos in adversarial examples. Chaos Solitons Fract 163:112577","journal-title":"Chaos Solitons Fract"},{"key":"10141_CR31","unstructured":"Vacanti G, Van Looveren A (2020) Adversarial detection and correction by matching prediction distributions. arXiv preprint arXiv:2002.09364"},{"issue":"3","key":"10141_CR32","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1016\/0167-2789(85)90011-9","volume":"16","author":"A Wolf","year":"1985","unstructured":"Wolf A, Swift JB, Swinney HL et al (1985) Determining lyapunov exponents from a time series. Phys D 16(3):285\u2013317","journal-title":"Phys D"},{"key":"10141_CR33","doi-asserted-by":"crossref","unstructured":"Bottou L, Cortes C, Denker JS, et al (1994) Comparison of classifier methods: a case study in handwritten digit recognition. In: Proceedings of the 12th IAPR international conference on pattern recognition, conference B: computer vision and image processing, vol 2. IEEE, Jerusalem, pp 77\u201382","DOI":"10.1109\/ICPR.1994.576879"},{"key":"10141_CR34","unstructured":"Xiao H, Rasul K, Vollgraf R (2017) Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747"},{"key":"10141_CR35","unstructured":"Krizhevsky A (2009) Learning multiple layers of features from tiny images. Technical Report TR-2009, University of Toronto"},{"issue":"7","key":"10141_CR36","doi-asserted-by":"crossref","first-page":"2578","DOI":"10.1109\/TNNLS.2019.2933590","volume":"31","author":"J Zhang","year":"2020","unstructured":"Zhang J, Li C (2020) Adversarial examples: opportunities and challenges. IEEE Trans Neural Netw Learn Syst 31(7):2578\u20132593","journal-title":"IEEE Trans Neural Netw Learn Syst"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10141-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-10141-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10141-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T06:11:06Z","timestamp":1726726266000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-10141-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,24]]},"references-count":36,"journal-issue":{"issue":"29","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["10141"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-10141-1","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,24]]},"assertion":[{"value":"11 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2024","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 associated with this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}