{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T17:18:12Z","timestamp":1769102292243,"version":"3.49.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,10,15]],"date-time":"2022-10-15T00:00:00Z","timestamp":1665792000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,10,15]],"date-time":"2022-10-15T00:00:00Z","timestamp":1665792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100012352","name":"Universit\u00e0 degli Studi di Milano","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100012352","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2023,2]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>This paper proposes a modeling scheme for cyber physical systems operating in non-stationary, small data environments. Unlike the traditional modeling logic, we introduce the few-shot learning paradigm, the operation of which is based on quantifying both similarities and dissimilarities. As such, we designed a suitable change detection mechanism able to reveal previously unknown operational states, which are incorporated in the dictionary online. We elaborate on spectrograms extracted from high-resolution ultrasound depth sensor timeseries, while the backbone of the proposed method is a Siamese Neural Network. The experimental scenario considers data representing liquid containers for fuel\/water when the following five operational states are present: <jats:italic>normal<\/jats:italic>, <jats:italic>accident<\/jats:italic>, <jats:italic>breakdown<\/jats:italic>, <jats:italic>sabotage<\/jats:italic>, and <jats:italic>cyber-attack<\/jats:italic>. Thorough experiments were carried out assessing every aspect of the present framework and demonstrating its efficacy even when very few samples per class are available. In addition, we propose a probabilistic data selection scheme facilitating one-shot learning. Last but not least, responding to the wide requirement for interpretable AI, we explain the obtained predictions by examining the layer-wise activation maps.<\/jats:p>","DOI":"10.1007\/s00521-022-07903-0","type":"journal-article","created":{"date-parts":[[2022,10,15]],"date-time":"2022-10-15T09:02:48Z","timestamp":1665824568000},"page":"3853-3863","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Few-shot learning for modeling cyber physical systems in non-stationary environments"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3482-9215","authenticated-orcid":false,"given":"Stavros","family":"Ntalampiras","sequence":"first","affiliation":[]},{"given":"Ilyas","family":"Potamitis","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,15]]},"reference":[{"issue":"4","key":"7903_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3430360","volume":"11","author":"S Samtani","year":"2020","unstructured":"Samtani S, Kantarcioglu M, Chen H (2020) Trailblazing the artificial intelligence for cybersecurity discipline. ACM Trans Manage Inf Syst 11(4):1\u201319. https:\/\/doi.org\/10.1145\/3430360","journal-title":"ACM Trans Manage Inf Syst"},{"key":"7903_CR2","doi-asserted-by":"publisher","first-page":"222310","DOI":"10.1109\/access.2020.3041951","volume":"8","author":"K Shaukat","year":"2020","unstructured":"Shaukat K, Luo S, Varadharajan V, Hameed IA, Xu M (2020) A survey on machine learning techniques for cyber security in the last decade. IEEE Access 8:222310\u2013222354. https:\/\/doi.org\/10.1109\/access.2020.3041951","journal-title":"IEEE Access"},{"issue":"1","key":"7903_CR3","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/TETCI.2017.2772792","volume":"2","author":"N Shone","year":"2018","unstructured":"Shone N, Ngoc TN, Phai VD, Shi Q (2018) A deep learning approach to network intrusion detection. IEEE Trans Emerg Top Comput Intell 2(1):41\u201350. https:\/\/doi.org\/10.1109\/TETCI.2017.2772792","journal-title":"IEEE Trans Emerg Top Comput Intell"},{"issue":"4","key":"7903_CR4","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1109\/TETC.2016.2606384","volume":"5","author":"A Mosenia","year":"2017","unstructured":"Mosenia A, Jha NK (2017) A comprehensive study of security of internet-of-things. IEEE Trans Emerg Top Comput 5(4):586\u2013602. https:\/\/doi.org\/10.1109\/TETC.2016.2606384","journal-title":"IEEE Trans Emerg Top Comput"},{"issue":"3","key":"7903_CR5","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1109\/TETC.2017.2787694","volume":"8","author":"C Liu","year":"2020","unstructured":"Liu C, Cronin P, Yang C (2020) Securing cyber-physical systems from hardware trojan collusion. IEEE Trans Emerg Top Comput 8(3):655\u2013667. https:\/\/doi.org\/10.1109\/TETC.2017.2787694","journal-title":"IEEE Trans Emerg Top Comput"},{"issue":"1","key":"7903_CR6","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TETCI.2016.2641452","volume":"1","author":"C Alippi","year":"2017","unstructured":"Alippi C, Ntalampiras S, Roveri M (2017) Model-free fault detection and isolation in large-scale cyber-physical systems. IEEE Trans Emerg Top Comput Intell 1(1):61\u201371. https:\/\/doi.org\/10.1109\/TETCI.2016.2641452","journal-title":"IEEE Trans Emerg Top Comput Intell"},{"key":"7903_CR7","doi-asserted-by":"publisher","unstructured":"Wan X, Han T, An J, Wu M (2021) Fault diagnosis for networked switched systems: An improved dynamic event-based scheme. IEEE Trans Cyber, pp 1\u201312. https:\/\/doi.org\/10.1109\/TCYB.2021.3049838","DOI":"10.1109\/TCYB.2021.3049838"},{"issue":"12","key":"7903_CR8","doi-asserted-by":"publisher","first-page":"3432","DOI":"10.1109\/TCYB.2018.2815758","volume":"48","author":"X Huang","year":"2018","unstructured":"Huang X, Dong J (2018) Reliable control policy of cyber-physical systems against a class of frequency-constrained sensor and actuator attacks. IEEE Trans Cyber 48(12):3432\u20133439. https:\/\/doi.org\/10.1109\/TCYB.2018.2815758","journal-title":"IEEE Trans Cyber"},{"key":"7903_CR9","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1016\/j.asoc.2015.10.011","volume":"38","author":"AA Aburomman","year":"2016","unstructured":"Aburomman AA, Reaz MBI (2016) A novel SVM-kNN-PSO ensemble method for intrusion detection system. Appl Soft Comput 38:360\u2013372. https:\/\/doi.org\/10.1016\/j.asoc.2015.10.011","journal-title":"Appl Soft Comput"},{"key":"7903_CR10","doi-asserted-by":"publisher","unstructured":"G\u00fcm\u00fc\u015fba\u015f D, Y\u0131ld\u0131r\u0131m T, Genovese A, Scotti F (2020) A comprehensive survey of databases and deep learning methods for cybersecurity and intrusion detection systems. IEEE Syst J, pp 1\u201315. https:\/\/doi.org\/10.1109\/JSYST.2020.2992966","DOI":"10.1109\/JSYST.2020.2992966"},{"issue":"7","key":"7903_CR11","doi-asserted-by":"publisher","first-page":"3081","DOI":"10.1109\/TCYB.2019.2940940","volume":"50","author":"R Coulter","year":"2020","unstructured":"Coulter R, Han Q-L, Pan L, Zhang J, Xiang Y (2020) Data-driven cyber security in perspective-intelligent traffic analysis. IEEE Trans Cyber 50(7):3081\u20133093. https:\/\/doi.org\/10.1109\/TCYB.2019.2940940","journal-title":"IEEE Trans Cyber"},{"key":"7903_CR12","doi-asserted-by":"publisher","unstructured":"Yang H-M, Zhang X-Y, Yin F, Yang Q, Liu C-L (2020) Convolutional prototype network for open set recognition, pp 1\u20131. https:\/\/doi.org\/10.1109\/tpami.2020.3045079","DOI":"10.1109\/tpami.2020.3045079"},{"key":"7903_CR13","doi-asserted-by":"publisher","unstructured":"Torralba A, Efros AA (2011) Unbiased look at dataset bias. In: CVPR 2011, pp 1521\u20131528. https:\/\/doi.org\/10.1109\/CVPR.2011.5995347","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"7903_CR14","doi-asserted-by":"crossref","unstructured":"Wang Y, Salamon J, Bryan NJ, Pablo Bello J (2020) Few-shot sound event detection. In: ICASSP 2020:81\u201385","DOI":"10.1109\/ICASSP40776.2020.9054708"},{"key":"7903_CR15","doi-asserted-by":"publisher","unstructured":"Ntalampiras S (2021) Speech emotion recognition via learning analogies 144:21\u201326. https:\/\/doi.org\/10.1016\/j.patrec.2021.01.018","DOI":"10.1016\/j.patrec.2021.01.018"},{"key":"7903_CR16","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1016\/j.dib.2017.07.038","volume":"14","author":"PM Laso","year":"2017","unstructured":"Laso PM, Brosset D, Puentes J (2017) Dataset of anomalies and malicious acts in a cyber-physical subsystem. Data Brief 14:186\u2013191. https:\/\/doi.org\/10.1016\/j.dib.2017.07.038","journal-title":"Data Brief"},{"key":"7903_CR17","unstructured":"European commission: white paper on artificial intelligence: a European approach to excellence and trust. Technical report, Brussels (19 February 2020)"},{"key":"7903_CR18","doi-asserted-by":"publisher","unstructured":"Alippi C, Ntalampiras S, Roveri M (2016) Online model-free sensor fault identification and dictionary learning in cyber-physical systems. In: 2016 International joint conference on neural networks (IJCNN), pp 756\u2013762. https:\/\/doi.org\/10.1109\/IJCNN.2016.7727276","DOI":"10.1109\/IJCNN.2016.7727276"},{"key":"7903_CR19","doi-asserted-by":"crossref","unstructured":"Bromley J, Guyon I, LeCun Y, S\u00e4ckinger E, Shah R (1994) Signature verification using a \u201csiamese\u201d time delay neural network. In: Cowan JD, Tesauro G, Alspector J (eds) Advances in neural information processing systems 6, pp 737\u2013744. Morgan-Kaufmann","DOI":"10.1142\/9789812797926_0003"},{"key":"7903_CR20","doi-asserted-by":"publisher","unstructured":"Piczak KJ (2015) Environmental sound classification with convolutional neural networks. In: 2015 IEEE 25th international workshop on machine learning for signal processing (MLSP), pp 1\u20136. https:\/\/doi.org\/10.1109\/MLSP.2015.7324337","DOI":"10.1109\/MLSP.2015.7324337"},{"issue":"2","key":"7903_CR21","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1109\/JSTSP.2019.2908700","volume":"13","author":"H Purwins","year":"2019","unstructured":"Purwins H, Li B, Virtanen T, Schl\u00fcter J, Chang S, Sainath T (2019) Deep learning for audio signal processing. IEEE J Selected Top Signal Process 13(2):206\u2013219. https:\/\/doi.org\/10.1109\/JSTSP.2019.2908700","journal-title":"IEEE J Selected Top Signal Process"},{"key":"7903_CR22","unstructured":"Koch G, Zemel R, Salakhutdinov R (2015) Siamese neural networks for one-shot image recognition"},{"key":"7903_CR23","doi-asserted-by":"publisher","unstructured":"Fei-Fei L, Fergus R, Perona P (2006) One-shot learning of object categories 28(4):594\u2013611. https:\/\/doi.org\/10.1109\/tpami.2006.79","DOI":"10.1109\/tpami.2006.79"},{"key":"7903_CR24","doi-asserted-by":"crossref","unstructured":"Taylor P (2006) The target cost formulation in unit selection speech synthesis. In: INTERSPEECH 2006, Pittsburgh, PA, USA. 17\u201321 Sept 2006","DOI":"10.21437\/Interspeech.2006-399"},{"key":"7903_CR25","doi-asserted-by":"publisher","unstructured":"Vitanyi PMB (2011) Information distance in multiples 57(4):2451\u20132456. https:\/\/doi.org\/10.1109\/tit.2011.2110130","DOI":"10.1109\/tit.2011.2110130"},{"issue":"3","key":"7903_CR26","doi-asserted-by":"publisher","first-page":"1852","DOI":"10.1109\/TII.2020.2988208","volume":"17","author":"L Feng","year":"2021","unstructured":"Feng L, Zhao C (2021) Fault description based attribute transfer for zero-sample industrial fault diagnosis. IEEE Trans Ind Inf 17(3):1852\u20131862. https:\/\/doi.org\/10.1109\/TII.2020.2988208","journal-title":"IEEE Trans Ind Inf"},{"key":"7903_CR27","doi-asserted-by":"publisher","unstructured":"Acconcjaioco M, Ntalampiras S (2021) One-shot learning for acoustic identification of bird species in non-stationary environments. In: 2020 ICPR, pp 755\u2013762. https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412005","DOI":"10.1109\/ICPR48806.2021.9412005"},{"issue":"9","key":"7903_CR28","doi-asserted-by":"publisher","first-page":"1939","DOI":"10.1109\/TNNLS.2014.2362015","volume":"26","author":"S Ntalampiras","year":"2015","unstructured":"Ntalampiras S (2015) Fault identification in distributed sensor networks based on universal probabilistic modeling. IEEE Trans Neural Netw Learn Syst 26(9):1939\u20131949. https:\/\/doi.org\/10.1109\/TNNLS.2014.2362015","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"7903_CR29","doi-asserted-by":"crossref","unstructured":"Garbuk SV (2018) Intellimetry as a way to ensure ai trustworthiness. In: 2018 International conference on artificial intelligence applications and innovations (IC-AIAI), pp 27\u201330","DOI":"10.1109\/IC-AIAI.2018.8674447"},{"key":"7903_CR30","doi-asserted-by":"publisher","first-page":"911","DOI":"10.1109\/TIFS.2019.2929409","volume":"15","author":"G Xu","year":"2020","unstructured":"Xu G, Li H, Liu S, Yang K, Lin X (2020) Verifynet: Secure and verifiable federated learning. IEEE Trans Inf Forensics Security 15:911\u2013926. https:\/\/doi.org\/10.1109\/TIFS.2019.2929409","journal-title":"IEEE Trans Inf Forensics Security"},{"key":"7903_CR31","unstructured":"Capgemini (2021) Reinventing cybersecurity with artificial intelligence: A new frontier in digital security. Technical report, Capgemini Research Institute. https:\/\/www.capgemini.com\/research\/reinventing-cybersecurity-with-artificial-intelligence\/"},{"issue":"2","key":"7903_CR32","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2019","unstructured":"Baltru\u0161aitis T, Ahuja C, Morency L-P (2019) Multimodal machine learning: a survey and taxonomy. IEEE Trans Pattern Anal Mach Intell 41(2):423\u2013443. https:\/\/doi.org\/10.1109\/TPAMI.2018.2798607","journal-title":"IEEE Trans Pattern Anal Mach Intell"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07903-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-07903-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07903-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T05:16:37Z","timestamp":1674796597000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-07903-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,15]]},"references-count":32,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,2]]}},"alternative-id":["7903"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-07903-0","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,15]]},"assertion":[{"value":"28 June 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 October 2022","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"}}]}}