Sascha Löbner is a research and teaching assistant at the Chair of Mobile Business & Multilateral Security. He holds a M.Sc. in Business Informatics and a B.Sc. in Economics and Business Administration, both from Goethe University Frankfurt. During his Master degree he specialized on Machine Learning, Distributed Systems and High Performance Computer Applications. His Master thesis on “Explainable Machine Learning for Default Privacy Setting Prediction” has been the key driver that led him to join the m-chair.

Currently, he is working in the field of Privacy Preserving Machine Learning and especially Federated Learning. 

Publications:

• S. Löbner, W. B. Tesfay, T. Nakamura and S. Pape, "Explainable Machine Learning for Default Privacy Setting Prediction," in IEEE Access, doi: 10.1109/ACCESS.2021.3074676.
• Sascha Löbner, Frédéric Tronnier, Sebastian Pape, and Kai Rannenberg. 2021. Comparison of De-Identification Techniques for Privacy Preserving Data Analysis in Vehicular Data Sharing. In Computer Science in Cars Symposium (CSCS '21). Association for Computing Machinery, New York, NY, USA, Article 7, 1–11. DOI: https://doi.org/10.1145/3488904.3493380
• Tronnier, F., Pape, S., Löbner, S., Rannenberg, K. (2022). A Discussion on Ethical Cybersecurity Issues in Digital Service Chains. In: Kołodziej, J., Repetto, M., Duzha, A. (eds) Cybersecurity of Digital Service Chains. Lecture Notes in Computer Science, vol 13300. Springer, Cham. https://doi.org/10.1007/978-3-031-04036-8_10
• Bracamonte, V., Pape, S., & Loebner, S. (2022). “All apps do this”: Comparing Privacy Concerns Towards Privacy Tools and Non-Privacy Tools for Social Media Content. Proceedings on Privacy Enhancing Technologies, 3, 57-78.
• Sascha Löbner, Christian Gartner, and Frédéric Tronnier. 2023. Privacy Preserving Data Analysis with the Encode, Shuffle, Analyse Architecture in Vehicular Data Sharing. In European Interdisciplinary Cybersecurity Conference (EICC2023). Association for Computing Machinery, New York, NY, USA, 85–91. https://doi.org/10.1145/3590777.3590791
• Löbner, S., Gogov, B., Tesfay, W.B. (2023). Enhancing Privacy in Federated Learning with Local Differential Privacy for Email Classification. In: Garcia-Alfaro, J., Navarro-Arribas, G., Dragoni, N. (eds) Data Privacy Management, Cryptocurrencies and Blockchain Technology. DPM CBT 2022 2022. Lecture Notes in Computer Science, vol 13619. Springer, Cham. https://doi.org/10.1007/978-3-031-25734-6_1
• Frédéric Tronnier, Patrick Biker, Erik Baur, and Sascha Löbner. 2023. An Evaluation of Information Flows in Digital Euro Transactions Using Contextual Integrity Theory. In European Interdisciplinary Cybersecurity Conference (EICC2023). Association for Computing Machinery, New York, NY, USA, 7–12. https://doi.org/10.1145/3590777.3590779
• Bracamonte, V., Pape, S., & Loebner, S. (2023). Comparing the Effect of Privacy and Non-Privacy Social Media Photo Tools on Factors of Privacy Concern. In ICISSP (pp. 669-676).
• Bracamonte, V., Pape, S., & Löbner, S. Factors of Intention to Use a Photo Tool: Comparison between Privacy-enhancing and Non-privacy-enhancing Tools. 
• Löbner, S., Pape, S., & Bracamonte, V. (2023, August). User Acceptance Criteria for Privacy Preserving Machine Learning Techniques. In Proceedings of the 18th International Conference on Availability, Reliability and Security (pp. 1-8).
• Bracamonte, V., Pape, S., Löbner, S., Frederic, T., (2023) Effectiveness and Information Quality Perception of an AI Model Card: A Study Among Non-Experts. In The 20th Annual International Conference on Privacy, Security & Trust (PST2023). 

• S. Löbner, W. B. Tesfay, Bracamonte, V., Nakamura, T., (2023) Systematizing the State of Knowledge in Detecting Privacy Sensitive Information in Unstructured Texts using Machine Learning. In The 20th Annual International Conference on Privacy, Security & Trust (PST2023).