TY - JOUR TI - The Missing Link in Network Intrusion Detection : taking AI/ML Research Efforts to Users AU - Dietz, Katharina AU - Mühlhauser, Michael AU - Kögel, Jochen AU - Schwinger, Stephan AU - Sichermann, Marleen AU - Seufert, Michael AU - Herrmann, Dominik AU - Hoßfeld, Tobias PY - 2025 SP - 79815-79837 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/110350 LA - deu AB - Intrusion Detection Systems (IDS) tackle the challenging task of detecting network attacks as fast as possible. As this is getting more complex in modern enterprise networks, Artificial Intelligence (AI) and Machine Learning (ML) have gained substantial popularity in research. However, their adoption into real-world IDS solutions remains poor. Academic research often overlooks the interconnection of users and technical aspects. This leads to less explainable AI/ML models that hinder trust among AI/ML non-experts. Additionally, research often neglects secondary concerns such as usability and privacy. If IDS approaches conflict with current regulations or if administrators cannot deal with attacks more effectively, enterprises will not adopt the IDS in practice. To identify those problems systematically, our literature survey takes a user-centric approach; we examine IDS research from the perspective of stakeholders by applying the concept of personas. Further, we investigate multiple factors limiting the adoption of AI/ML in security and suggest technical, non-technical, and user-related considerations to enhance the adoption in practice. Our key contributions are threefold. (i) We derive personas from realistic enterprise scenarios, (ii) we provide a set of relevant hypotheses in the form of a review template, and (iii), based on our reviews, we derive design guidelines for practical implementations. To the best of our knowledge, this is the first paper that analyzes practical adoption barriers of AI/ML-based intrusion detection solutions concerning appropriateness of data, reproducibility, explainability, practicability, usability, and privacy. Our guidelines may help researchers to holistically evaluate their AI/ML-based IDS approaches to increase practical adoption. KW - Anomaly detection KW - artifcial intelligence KW - intrusion detection KW - machine learning KW - network monitoring KW - privacy KW - security KW - usability ER - TY - JOUR TI - The Missing Link in Network Intrusion Detection : taking AI/ML Research Efforts to Users AU - Dietz, Katharina AU - Mühlhauser, Michael AU - Kögel, Jochen AU - Schwinger, Stephan AU - Sichermann, Marleen AU - Seufert, Michael AU - Herrmann, Dominik AU - Hoßfeld, Tobias PY - 2024 JO - IEEE access : practical research, open solutions VL - 12 SP - 79815-79837 PB - IEEE CY - New York SN - 2169-3536 DO - 10.1109/access.2024.3406939 UR - https://fis.uni-bamberg.de/handle/uniba/95436 LA - deu AB - Intrusion Detection Systems (IDS) tackle the challenging task of detecting network attacks as fast as possible. As this is getting more complex in modern enterprise networks, Artificial Intelligence (AI) and Machine Learning (ML) have gained substantial popularity in research. However, their adoption into real-world IDS solutions remains poor. Academic research often overlooks the interconnection of users and technical aspects. This leads to less explainable AI/ML models that hinder trust among AI/ML non-experts. Additionally, research often neglects secondary concerns such as usability and privacy. If IDS approaches conflict with current regulations or if administrators cannot deal with attacks more effectively, enterprises will not adopt the IDS in practice. To identify those problems systematically, our literature survey takes a user-centric approach; we examine IDS research from the perspective of stakeholders by applying the concept of personas. Further, we investigate multiple factors limiting the adoption of AI/ML in security and suggest technical, non-technical, and user-related considerations to enhance the adoption in practice. Our key contributions are threefold. (i) We derive personas from realistic enterprise scenarios, (ii) we provide a set of relevant hypotheses in the form of a review template, and (iii), based on our reviews, we derive design guidelines for practical implementations. To the best of our knowledge, this is the first paper that analyzes practical adoption barriers of AI/ML-based intrusion detection solutions concerning appropriateness of data, reproducibility, explainability, practicability, usability, and privacy. Our guidelines may help researchers to holistically evaluate their AI/ML-based IDS approaches to increase practical adoption. KW - Anomaly detection KW - artifcial intelligence KW - intrusion detection KW - machine learning KW - network monitoring KW - privacy KW - security KW - usability ER - TY - CPAPER TI - Towards Anonymizing Intermodal Mobility Data for Smart Cities AU - Ackermann, Leonie AU - Mühlhauser, Michael AU - Burdusel, Alexandru AU - Federlin, Michael AU - Herrmann, Dominik AU - Holly, Steffen AU - Nicklas, Daniela AU - Wolpert, Daniel PY - 2024 SP - 1-6 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/92663 LA - eng AB - As cities seek to optimize their resources for a sustainable and livable future, the concept of intermodal mobility has become increasingly important. However, the collection and analysis of intermodal mobility data is complicated by the need for robust anonymization methods, as privacy and security concerns remain paramount. Existing anonymization methods are either mode-specific or so complicated that they deter potential stakeholders. In this paper, we describe a variety of real mobility data sources for our upcoming field study. With that data, we plan to provide insights into infrastructure utilization and transitions between modes of transport. We further identified several anonymization techniques for mobility data to ensure privacy and acceptance among the citizens. To find suitable techniques for intermodal mobility data, we provide insights from our previous experience on anonymization and discuss the practicability of the identified techniques. Our paper highlights the need for explainable anonymization methods tailored to intermodal mobility data that address privacy and security concerns and pave the way for more accessible privacy-compliant solutions. KW - Intermodal Mobility KW - Smart Cities KW - Anonymization KW - Privacy ER - TY - CPAPER TI - Towards Anonymizing Intermodal Mobility Data for Smart Cities AU - Ackermann, Leonie AU - Mühlhauser, Michael AU - Burdusel, Alexandru AU - Federlin, Michael AU - Herrmann, Dominik AU - Holly, Steffen AU - Nicklas, Daniela AU - Wolpert, Daniel PY - 2023 T2 - GeoPrivacy '23: Proceedings of the 1st ACM SIGSPATIAL International Workshop on Geo-Privacy and Data Utility for Smart Societies SP - 24-27 CY - New York DO - 10.1145/3615889.3628514 UR - https://fis.uni-bamberg.de/handle/uniba/92608 LA - eng AB - As cities seek to optimize their resources for a sustainable and livable future, the concept of intermodal mobility has become increasingly important. However, the collection and analysis of intermodal mobility data is complicated by the need for robust anonymization methods, as privacy and security concerns remain paramount. Existing anonymization methods are either mode-specific or so complicated that they deter potential stakeholders. In this paper, we describe a variety of real mobility data sources for our upcoming field study. With that data, we plan to provide insights into infrastructure utilization and transitions between modes of transport. We further identified several anonymization techniques for mobility data to ensure privacy and acceptance among the citizens. To find suitable techniques for intermodal mobility data, we provide insights from our previous experience on anonymization and discuss the practicability of the identified techniques. Our paper highlights the need for explainable anonymization methods tailored to intermodal mobility data that address privacy and security concerns and pave the way for more accessible privacy-compliant solutions. KW - Intermodal Mobility KW - Smart Cities KW - Anonymization KW - Privacy ER - TY - CPAPER TI - How Private is Android’s Private DNS Setting? : Identifying Apps by Encrypted DNS Traffic AU - Mühlhauser, Michael AU - Pridöhl, Henning AU - Herrmann, Dominik PY - 2021 T2 - ARES 2021: The 16th International Conference on Availability, Reliability and Security, proceedings PB - ACM CY - New York, NY SN - 978-1-4503-9051-4 DO - 10.1145/3465481.3465764 UR - https://fis.uni-bamberg.de/handle/uniba/53782 LA - eng ER -