{"author":[{"id":"67200","first_name":"Arnab","full_name":"Sharma, Arnab","last_name":"Sharma"},{"id":"43817","first_name":"Caglar","last_name":"Demir","full_name":"Demir, Caglar"},{"first_name":"Axel-Cyrille","full_name":"Ngonga Ngomo, Axel-Cyrille","last_name":"Ngonga Ngomo","id":"65716"},{"id":"573","first_name":"Heike","last_name":"Wehrheim","full_name":"Wehrheim, Heike"}],"department":[{"_id":"7"},{"_id":"77"},{"_id":"574"}],"status":"public","project":[{"_id":"1","name":"SFB 901"},{"_id":"3","name":"SFB 901 - Project Area B"},{"_id":"11","name":"SFB 901 - Subproject B3"},{"_id":"10","name":"SFB 901 - Subproject B2"}],"year":"2021","type":"conference","user_id":"477","publication_status":"accepted","date_created":"2021-12-07T11:11:36Z","language":[{"iso":"eng"}],"publisher":"IEEE","abstract":[{"lang":"eng","text":"In recent years, we observe an increasing amount of software with machine learning components being deployed. This poses the question of quality assurance for such components: how can we validate whether specified requirements are fulfilled by a machine learned software? Current testing and verification approaches either focus on a single requirement (e.g., fairness) or specialize on a single type of machine learning model (e.g., neural networks).\r\nIn this paper, we propose property-driven testing of machine learning models. Our approach MLCheck encompasses (1) a language for property specification, and (2) a technique for systematic test case generation. The specification language is comparable to property-based testing languages. Test case generation employs advanced verification technology for a systematic, property dependent construction of test suites, without additional user supplied generator functions. We evaluate MLCheck using requirements and data sets from three different application areas (software\r\ndiscrimination, learning on knowledge graphs and security). Our evaluation shows that despite its generality MLCheck can even outperform specialised testing approaches while having a comparable runtime"}],"_id":"28350","date_updated":"2022-01-06T06:58:02Z","publication":"Proceedings of the 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","title":"MLCHECK–Property-Driven Testing of Machine Learning Classifiers","citation":{"ama":"Sharma A, Demir C, Ngonga Ngomo A-C, Wehrheim H. MLCHECK–Property-Driven Testing of Machine Learning Classifiers. In: Proceedings of the 20th IEEE International Conference on Machine Learning and Applications (ICMLA). IEEE.","bibtex":"@inproceedings{Sharma_Demir_Ngonga Ngomo_Wehrheim, title={MLCHECK–Property-Driven Testing of Machine Learning Classifiers}, booktitle={Proceedings of the 20th IEEE International Conference on Machine Learning and Applications (ICMLA)}, publisher={IEEE}, author={Sharma, Arnab and Demir, Caglar and Ngonga Ngomo, Axel-Cyrille and Wehrheim, Heike} }","ieee":"A. Sharma, C. Demir, A.-C. Ngonga Ngomo, and H. Wehrheim, “MLCHECK–Property-Driven Testing of Machine Learning Classifiers.”","short":"A. Sharma, C. Demir, A.-C. Ngonga Ngomo, H. Wehrheim, in: Proceedings of the 20th IEEE International Conference on Machine Learning and Applications (ICMLA), IEEE, n.d.","mla":"Sharma, Arnab, et al. “MLCHECK–Property-Driven Testing of Machine Learning Classifiers.” Proceedings of the 20th IEEE International Conference on Machine Learning and Applications (ICMLA), IEEE.","apa":"Sharma, A., Demir, C., Ngonga Ngomo, A.-C., & Wehrheim, H. (n.d.). MLCHECK–Property-Driven Testing of Machine Learning Classifiers. Proceedings of the 20th IEEE International Conference on Machine Learning and Applications (ICMLA).","chicago":"Sharma, Arnab, Caglar Demir, Axel-Cyrille Ngonga Ngomo, and Heike Wehrheim. “MLCHECK–Property-Driven Testing of Machine Learning Classifiers.” In Proceedings of the 20th IEEE International Conference on Machine Learning and Applications (ICMLA). IEEE, n.d."}}