{"department":[{"_id":"ToHe"}],"oa_version":"Published Version","doi":"10.1007/s10009-023-00711-4","project":[{"_id":"62781420-2b32-11ec-9570-8d9b63373d4d","name":"Vigilant Algorithmic Monitoring of Software","grant_number":"101020093","call_identifier":"H2020"}],"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","type":"journal_article","date_updated":"2024-01-30T12:06:57Z","file_date_updated":"2024-01-30T12:06:07Z","acknowledgement":"This work was supported in part by the ERC-2020-AdG 101020093, by DIREC - Digital Research Centre Denmark, and by the Villum Investigator Grant S4OS.","ec_funded":1,"_id":"13234","file":[{"relation":"main_file","file_id":"14903","content_type":"application/pdf","file_name":"2023_JourSoftwareTools_Kueffner.pdf","checksum":"3c4b347f39412a76872f9a6f30101f94","date_created":"2024-01-30T12:06:07Z","file_size":13387667,"date_updated":"2024-01-30T12:06:07Z","success":1,"creator":"dernst","access_level":"open_access"}],"status":"public","article_type":"original","license":"https://creativecommons.org/licenses/by/4.0/","publisher":"Springer Nature","external_id":{"isi":["001020160000001"],"arxiv":["2009.06429"]},"date_created":"2023-07-16T22:01:11Z","month":"08","publication_status":"published","publication":"International Journal on Software Tools for Technology Transfer","has_accepted_license":"1","tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png"},"article_processing_charge":"Yes (in subscription journal)","citation":{"ista":"Kueffner K, Lukina A, Schilling C, Henzinger TA. 2023. Into the unknown: Active monitoring of neural networks (extended version). International Journal on Software Tools for Technology Transfer. 25, 575–592.","mla":"Kueffner, Konstantin, et al. “Into the Unknown: Active Monitoring of Neural Networks (Extended Version).” <i>International Journal on Software Tools for Technology Transfer</i>, vol. 25, Springer Nature, 2023, pp. 575–92, doi:<a href=\"https://doi.org/10.1007/s10009-023-00711-4\">10.1007/s10009-023-00711-4</a>.","short":"K. Kueffner, A. Lukina, C. Schilling, T.A. Henzinger, International Journal on Software Tools for Technology Transfer 25 (2023) 575–592.","ama":"Kueffner K, Lukina A, Schilling C, Henzinger TA. Into the unknown: Active monitoring of neural networks (extended version). <i>International Journal on Software Tools for Technology Transfer</i>. 2023;25:575-592. doi:<a href=\"https://doi.org/10.1007/s10009-023-00711-4\">10.1007/s10009-023-00711-4</a>","apa":"Kueffner, K., Lukina, A., Schilling, C., &#38; Henzinger, T. A. (2023). Into the unknown: Active monitoring of neural networks (extended version). <i>International Journal on Software Tools for Technology Transfer</i>. Springer Nature. <a href=\"https://doi.org/10.1007/s10009-023-00711-4\">https://doi.org/10.1007/s10009-023-00711-4</a>","chicago":"Kueffner, Konstantin, Anna Lukina, Christian Schilling, and Thomas A Henzinger. “Into the Unknown: Active Monitoring of Neural Networks (Extended Version).” <i>International Journal on Software Tools for Technology Transfer</i>. Springer Nature, 2023. <a href=\"https://doi.org/10.1007/s10009-023-00711-4\">https://doi.org/10.1007/s10009-023-00711-4</a>.","ieee":"K. Kueffner, A. Lukina, C. Schilling, and T. A. Henzinger, “Into the unknown: Active monitoring of neural networks (extended version),” <i>International Journal on Software Tools for Technology Transfer</i>, vol. 25. Springer Nature, pp. 575–592, 2023."},"intvolume":"        25","related_material":{"record":[{"relation":"shorter_version","status":"public","id":"10206"}]},"title":"Into the unknown: Active monitoring of neural networks (extended version)","ddc":["000"],"publication_identifier":{"issn":["1433-2779"],"eissn":["1433-2787"]},"scopus_import":"1","quality_controlled":"1","date_published":"2023-08-01T00:00:00Z","volume":25,"oa":1,"abstract":[{"lang":"eng","text":"Neural-network classifiers achieve high accuracy when predicting the class of an input that they were trained to identify. Maintaining this accuracy in dynamic environments, where inputs frequently fall outside the fixed set of initially known classes, remains a challenge. We consider the problem of monitoring the classification decisions of neural networks in the presence of novel classes. For this purpose, we generalize our recently proposed abstraction-based monitor from binary output to real-valued quantitative output. This quantitative output enables new applications, two of which we investigate in the paper. As our first application, we introduce an algorithmic framework for active monitoring of a neural network, which allows us to learn new classes dynamically and yet maintain high monitoring performance. As our second application, we present an offline procedure to retrain the neural network to improve the monitor’s detection performance without deteriorating the network’s classification accuracy. Our experimental evaluation demonstrates both the benefits of our active monitoring framework in dynamic scenarios and the effectiveness of the retraining procedure."}],"year":"2023","isi":1,"page":"575-592","language":[{"iso":"eng"}],"day":"01","author":[{"first_name":"Konstantin","orcid":"0000-0001-8974-2542","last_name":"Kueffner","full_name":"Kueffner, Konstantin","id":"8121a2d0-dc85-11ea-9058-af578f3b4515"},{"first_name":"Anna","last_name":"Lukina","full_name":"Lukina, Anna","id":"CBA4D1A8-0FE8-11E9-BDE6-07BFE5697425"},{"first_name":"Christian","last_name":"Schilling","orcid":"0000-0003-3658-1065","full_name":"Schilling, Christian","id":"3A2F4DCE-F248-11E8-B48F-1D18A9856A87"},{"full_name":"Henzinger, Thomas A","id":"40876CD8-F248-11E8-B48F-1D18A9856A87","first_name":"Thomas A","last_name":"Henzinger","orcid":"0000-0002-2985-7724"}]}