Prof. Dr. Benjamin Weggenmann
Fakultät Informatik und Wirtschaftsinformatik
Lehrgebiete
Lehrveranstaltungen
Bachelor Informationssicherheit (BISD)
- AI and Security
- OS Exploitation
- Security Engineering
- Security Operations
Forschungsschwerpunkte
Forschungsinteressen
Data security and privacy
- Privacy-Enhancing Technologies (PETs)
- Differential Privacy
- Privacy-Preserving Machine Learning
- Cryptography
Software Security
- Vulnerability Detection
- Static and Dynamic Analysis
Publikationen
Ausgewählte Publikationen
Eine aktuelle Liste an Publikationen findet sich unter DBLP oder Google Scholar.
Hier ist eine Auswahl einiger begutachteter Publikationen:
- Weggenmann, B., & Kerschbaum, F. (2018). SynTF: Synthetic and Differentially Private Term Frequency Vectors for Privacy-Preserving Text Mining. Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. DOI: doi.org/10.1145/3209978.3210008.
- Weggenmann, B., & Kerschbaum, F. (2021). Differential Privacy for Directional Data. Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security (CCS). DOI: doi.org/10.1145/3460120.3484734.
- Weggenmann, B., Rublack, V., Andrejczuk, M., Mattern, J., & Kerschbaum, F. (2022). DP-VAE: Human-Readable Text Anonymization for Online Reviews with Differentially Private Variational Autoencoders. Proceedings of the ACM Web Conference 2022 (WWW). DOI: doi.org/10.1145/3485447.3512232.
- Mattern, J., Jin, Z., Weggenmann, B., Schölkopf, B., & Sachan, M. (2022). Differentially Private Language Models for Secure Data Sharing. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP). DOI: doi.org/10.18653/v1/2022.emnlp-main.579.
- Mattern, J., Weggenmann, B., & Kerschbaum, F. (2022). The Limits of Word Level Differential Privacy. Findings of the Association for Computational Linguistics: NAACL 2022. DOI: doi.org/10.18653/v1/2022.findings-naacl.65.
- Capano, F., Böhler, J., & Weggenmann, B. (2026). SPRINT: Scalable Secure & Differentially Private Inference for Transformers. Proceedings on Privacy Enhancing Technologies (PoPETs). DOI: doi.org/10.56553/popets-2026-0008.
- Capano, F., Böhler, J., & Weggenmann, B. (2026). SoK: Enhancing Cryptographic Collaborative Learning with Differential Privacy. IEEE Conference on Secure and Trustworthy Machine Learning (SaTML 2026). DOI: doi.org/10.48550/arXiv.2601.09460.