2026W

• Bachelor Thesis / 192.061 / PR
• Explainable AI / 192.217 / VU
• Machine Learning for Computer Security / 192.172 / VU
• Project in Computer Science 1 / 192.021 / PR
• Project in Computer Science 2 / 192.022 / PR
• Seminar for PhD Students / 192.060 / SE

2027S

• Project in Computer Science 2 / 192.022 / PR

• Building Robust and Explainable AI-based Defenses for Computer Security
  2024 – 2030 / Vienna Science and Technology Fund (WWTF)
  Publications: 223656 / 222934 / 222191 / 230094 / 230328 / 230269

• Towards Explaining Classification Models in Security with Sparse Autoencoders / Breuer, N. O., Linhardt, L., Normann, P., & Arp, D. (2026). Towards Explaining Classification Models in Security with Sparse Autoencoders. In 2026 IEEE European Symposium on Security and Privacy Workshops (EuroS&PW) (pp. 278–289). IEEE. https://doi.org/10.1109/EuroSPW72509.2026.00041
  Project: BREADS (2024–2030)
• Chasing Shadows: Pitfalls in LLM Security Research / Jonathan Evertz, Risse, N., Neuer, N., Müller, A., Normann, P., Sapia, G., Gupta, S., Pape, D., Shaw, S., Srivastav, D., Wressnegger, C., Quiring, E., Eisenhofer, T., Arp, D., & Schönherr, L. (2026). Chasing Shadows: Pitfalls in LLM Security Research. In Proceedings 2026 Network and Distributed System Security Symposium. Network and Distributed System Security (NDSS) Symposium 2026, San Diego, CA, United States of America (the). Schloss Dagstuhl. https://doi.org/10.14722/ndss.2026.241749
  Project: BREADS (2024–2030)
• Intriguing Properties of Adversarial ML Attacks in the Problem Space [Extended Version] / Cortellazzi, J., Quiring, E., Arp, D., Pendlebury, F., Pierazzi, F., & Cavallaro, L. (2025). Intriguing Properties of Adversarial ML Attacks in the Problem Space [Extended Version]. ACM Transactions on Privacy and Security, 28(4), 1–37. https://doi.org/10.1145/3742895
  Project: BREADS (2024–2030)
• Rule Extraction and Interaction-Aware Explainability for AI-Driven Malware Detection / Anthony, P., Galadima, K. R., Adams, Z., Onoja, M., Arp, D., Homola, M., & Balogh, Š. (2025). Rule Extraction and Interaction-Aware Explainability for AI-Driven Malware Detection. In A. Hogan, K. Satoh, H. Dağ, A.-Y. Turhan, D. Roman, & A. Soylu (Eds.), Rules and Reasoning : 9th International Joint Conference, RuleML+RR 2025, Istanbul, Turkey, September 22–24, 2025, Proceedings (pp. 137–155). Springer. https://doi.org/10.1007/978-3-032-08887-1_9
  Project: BREADS (2024–2030)
• Seeing through: analyzing and attacking virtual backgrounds in video calls / Weißberg, F., Hilgefort, J. M., Grogorick, S., Arp, D., Eisenhofer, T., Eisemann, M., & Rieck, K. (2025). Seeing through: analyzing and attacking virtual backgrounds in video calls. In SEC ’25: Proceedings of the 34th USENIX Conference on Security Symposium (pp. 6561–6580). Association for Computing Machinery. http://hdl.handle.net/20.500.12708/222934
  Project: BREADS (2024–2030)
• Pitfalls in Machine Learning for Computer Security / Arp, D., Quiring, E., Pendlebury, F., Warnecke, A., Pierazzi, F., Wressnegger, C., Cavallaro, L., & Rieck, K. (2024). Pitfalls in Machine Learning for Computer Security. Communications of the ACM, 67(11), 104–112. https://doi.org/10.1145/3643456
  Download: Artikel (1.17 MB)

• User behavior simulation with large language models for security evaluation / Moser, L. (2026). User behavior simulation with large language models for security evaluation [Diploma Thesis, Technische Universität Wien]. reposiTUm. https://doi.org/10.34726/hss.2026.132647
  Download: PDF (6.22 MB)