Stefan Czybik
Stefan Czybik
Doctoral Researcher
- mobil security
- side-channels
- mobil privacy
Anne Josiane Kouam, Stefan Czybik, Konrad Rieck
Sans GPS ni permission : inférer les déplacements d'usagers en transport public
Stefan Czybik, Anne Josiane Kouam , Peter Heubl, Jan Magnus Nold, Konrad Rieck
A Large-Scale Study of Personalized Phishing using Large Language Models
Stefan Czybik, Micha Horlboge, Konrad Rieck
Lazy Gatekeepers: A Large-Scale Study on SPF Configuration in the Wild
Stefan Czybik, Daniel Arp, Konrad Rieck
Quantifying the Risk of Wormhole Attacks on Bluetooth Contact Tracing
AI Goes Phishing
BIFOLD study, co-authored by members of the Machine Learning and Security Group, shows AI-generated phishing emails are three times as effective as generic ones and cost next to nothing. The field experiment with 7,700 participants provides the first large-scale evidence of how cheaply and effectively language models can personalize phishing. The paper will be presented at the USENIX Security Symposium 2026.
SaTML 2026 Conference Contributions
BIFOLD supports this year's IEEE SaTML, which is held from March 23 to 25 at the Technical University of Munich.