{"external_id":{"isi":["000719383800003"],"arxiv":["2009.06429"]},"author":[{"last_name":"Lukina","id":"CBA4D1A8-0FE8-11E9-BDE6-07BFE5697425","first_name":"Anna","full_name":"Lukina, Anna"},{"full_name":"Schilling, Christian","first_name":"Christian","id":"3A2F4DCE-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0003-3658-1065","last_name":"Schilling"},{"full_name":"Henzinger, Thomas A","first_name":"Thomas A","id":"40876CD8-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0002-2985-7724","last_name":"Henzinger"}],"date_updated":"2024-01-30T12:06:56Z","user_id":"4359f0d1-fa6c-11eb-b949-802e58b17ae8","year":"2021","_id":"10206","doi":"10.1007/978-3-030-88494-9_3","quality_controlled":"1","alternative_title":["LNCS"],"isi":1,"publication_status":"published","volume":"12974 ","scopus_import":"1","main_file_link":[{"url":"https://arxiv.org/abs/2009.06429","open_access":"1"}],"keyword":["monitoring","neural networks","novelty detection"],"month":"10","publication":"21st International Conference on Runtime Verification","citation":{"ista":"Lukina A, Schilling C, Henzinger TA. 2021. Into the unknown: active monitoring of neural networks. 21st International Conference on Runtime Verification. RV: Runtime Verification, LNCS, vol. 12974, 42–61.","mla":"Lukina, Anna, et al. “Into the Unknown: Active Monitoring of Neural Networks.” <i>21st International Conference on Runtime Verification</i>, vol. 12974, Springer Nature, 2021, pp. 42–61, doi:<a href=\"https://doi.org/10.1007/978-3-030-88494-9_3\">10.1007/978-3-030-88494-9_3</a>.","apa":"Lukina, A., Schilling, C., &#38; Henzinger, T. A. (2021). Into the unknown: active monitoring of neural networks. In <i>21st International Conference on Runtime Verification</i> (Vol. 12974, pp. 42–61). Cham: Springer Nature. <a href=\"https://doi.org/10.1007/978-3-030-88494-9_3\">https://doi.org/10.1007/978-3-030-88494-9_3</a>","ama":"Lukina A, Schilling C, Henzinger TA. Into the unknown: active monitoring of neural networks. In: <i>21st International Conference on Runtime Verification</i>. Vol 12974. Cham: Springer Nature; 2021:42-61. doi:<a href=\"https://doi.org/10.1007/978-3-030-88494-9_3\">10.1007/978-3-030-88494-9_3</a>","chicago":"Lukina, Anna, Christian Schilling, and Thomas A Henzinger. “Into the Unknown: Active Monitoring of Neural Networks.” In <i>21st International Conference on Runtime Verification</i>, 12974:42–61. Cham: Springer Nature, 2021. <a href=\"https://doi.org/10.1007/978-3-030-88494-9_3\">https://doi.org/10.1007/978-3-030-88494-9_3</a>.","short":"A. Lukina, C. Schilling, T.A. Henzinger, in:, 21st International Conference on Runtime Verification, Springer Nature, Cham, 2021, pp. 42–61.","ieee":"A. Lukina, C. Schilling, and T. A. Henzinger, “Into the unknown: active monitoring of neural networks,” in <i>21st International Conference on Runtime Verification</i>, Virtual, 2021, vol. 12974, pp. 42–61."},"related_material":{"record":[{"status":"public","relation":"extended_version","id":"13234"}]},"status":"public","acknowledgement":"We thank Christoph Lampert and Alex Greengold for fruitful discussions. This research was supported in part by the Simons Institute for the Theory of Computing, the Austrian Science Fund (FWF) under grant Z211-N23 (Wittgenstein Award), and the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 754411.","publication_identifier":{"issn":["0302-9743"],"eisbn":["978-3-030-88494-9"],"eissn":["1611-3349"],"isbn":["9-783-0308-8493-2"]},"date_created":"2021-10-31T23:01:31Z","language":[{"iso":"eng"}],"article_processing_charge":"No","title":"Into the unknown: active monitoring of neural networks","page":"42-61","day":"06","project":[{"_id":"260C2330-B435-11E9-9278-68D0E5697425","grant_number":"754411","name":"ISTplus - Postdoctoral Fellowships","call_identifier":"H2020"},{"name":"The Wittgenstein Prize","grant_number":"Z211","_id":"25F42A32-B435-11E9-9278-68D0E5697425","call_identifier":"FWF"}],"place":"Cham","type":"conference","publisher":"Springer Nature","department":[{"_id":"ToHe"}],"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. The typical approach is to detect inputs from novel classes and retrain the classifier on an augmented dataset. However, not only the classifier but also the detection mechanism needs to adapt in order to distinguish between newly learned and yet unknown input classes. To address this challenge, we introduce an algorithmic framework for active monitoring of a neural network. A monitor wrapped in our framework operates in parallel with the neural network and interacts with a human user via a series of interpretable labeling queries for incremental adaptation. In addition, we propose an adaptive quantitative monitor to improve precision. An experimental evaluation on a diverse set of benchmarks with varying numbers of classes confirms the benefits of our active monitoring framework in dynamic scenarios."}],"ec_funded":1,"conference":{"name":"RV: Runtime Verification","start_date":"2021-10-11","end_date":"2021-10-14","location":"Virtual"},"date_published":"2021-10-06T00:00:00Z","oa_version":"Preprint"}