{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/safeml-safety-monitoring-of-machine-learning","title":"SafeML: Safety Monitoring of Machine Learning Classifiers through Statistical Difference Measure","arxiv_id":"2005.13166","date":"2020-05-27","proceeding":null,"authors":["Koorosh Aslansefat","Ioannis Sorokos","Declan Whiting","Ramin Tavakoli Kolagari","Yiannis Papadopoulos"],"abstract":"Ensuring safety and explainability of machine learning (ML) is a topic of increasing relevance as data-driven applications venture into safety-critical application domains, traditionally committed to high safety standards that are not satisfied with an exclusive testing approach of otherwise inaccessible black-box systems. Especially the interaction between safety and security is a central challenge, as security violations can lead to compromised safety. The contribution of this paper to addressing both safety and security within a single concept of protection applicable during the operation of ML systems is active monitoring of the behaviour and the operational context of the data-driven system based on distance measures of the Empirical Cumulative Distribution Function (ECDF). We investigate abstract datasets (XOR, Spiral, Circle) and current security-specific datasets for intrusion detection (CICIDS2017) of simulated network traffic, using distributional shift detection measures including the Kolmogorov-Smirnov, Kuiper, Anderson-Darling, Wasserstein and mixed Wasserstein-Anderson-Darling measures. Our preliminary findings indicate that the approach can provide a basis for detecting whether the application context of an ML component is valid in the safety-security. Our preliminary code and results are available at https://github.com/ISorokos/SafeML.","url_abs":"https://arxiv.org/abs/2005.13166v1","url_pdf":"https://arxiv.org/pdf/2005.13166v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"safeml-safety-monitoring-of-machine-learning","repo_url":"https://github.com/ISorokos/SafeML","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"safeml-safety-monitoring-of-machine-learning","repo_url":"https://github.com/n-akram/SafeML","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"intrusion-detection","task_name":"Intrusion Detection"},{"task_slug":"safe-exploration","task_name":"Safe Exploration"},{"task_slug":null,"task_name":"valid"}],"methods":[{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"gaussian-process","method_name":"Gaussian Process"},{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/classification-on-xor","task":"General Classification","dataset":"XOR","model":"KNN","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"93.1045"},"uses_additional_data":false},{"leaderboard":"/sota/classification-on-xor","task":"General Classification","dataset":"XOR","model":"RF","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"92.962"},"uses_additional_data":false},{"leaderboard":"/sota/classification-on-xor","task":"General Classification","dataset":"XOR","model":"CART","rank_in_archive_order":3,"of":4,"metrics":{"Accuracy":"92.8179"},"uses_additional_data":false},{"leaderboard":"/sota/classification-on-xor","task":"General Classification","dataset":"XOR","model":"LDA","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"77.2217"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}