Faculty
Thorsten Eisenhofer is a tenure-track faculty at CISPA Helmholtz Center for Information Security in Saarbrücken, Germany. He previously worked as a postdoctoral researcher at BIFOLD and TU Berlin and earned his PhD from Ruhr University Bochum, where he was part of the Cluster of Excellence CASA. His research focuses on machine learning and computer security, particularly on attacks against learning-based models and defenses to improve their robustness. This work often involves looking beyond the model itself and examining the entire computational pipeline, including the underlying hardware and software stack.
ACM ASIA Conference on Computer and Communications Security (AsiaCCS) SoK: Where to Fuzz? Assessing Target Selection Methods in Directed Fuzzing
IEEE Symposium on Security and Privacy (S&P) A Representative Study on Human Detection of Artificially Generated Media Across Countries
ACM ASIA Conference on Computer and Communications Security (AsiaCCS) Cross-Language Differential Testing of JSON Parsers
Network and Distributed System Security Symposium (NDSS) Drone Security and the Mysterious Case of DJI's DroneID
IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) VENOMAVE: Targeted Poisoning Against Speech Recognition
Usenix Security Symposium (USENIX-Security) No more Reviewer #2: Subverting Automatic Paper-Reviewer Assignment using Adversarial Learning
Computer Speech and Language Exploring Accidental Triggers of Smart Speakers
Advances in Cryptology (CRYPTO) Password-Authenticated Key Exchange from Group Actions
Usenix Security Symposium (USENIX-Security) Dompteur: Taming Audio Adversarial Examples
Annual Computer Security Applications Conference (ACSAC) Imperio: Robust Over-the-Air Adversarial Examples for Automatic Speech Recognition Systems