Biometrics and Internet Security Research Group | dasec
The current funding for CRISP (BMBF and HMWK) and further third party funded projects (e.g. from BMBF, BSI, industry) allows us to employ motivated and outstanding staff members to work on their PhD in the area of IT security. Ten good reasons for
Claudia-Ioana Satnoianu defended her Master Thesis on Face Recognition, Effects and Detection of Beautification Applications The goal of this MSc thesis is to analyze the impact beautification apps can have on face recognition systems and to see if detection systems
CRISP scientists (P. Drozdowski, Dr. C. Rathgeb, Prof. Dr. C. Busch) from Hochschule Darmstadt investigated the topic of efficient biometric identification from both the academic and industry perspective. The work was conducted in the context of LOEWE-3 sponsored project BioBiDa
Together with international experts, CRISP scientists from Hochschule Darmstadt and TU Darmstadt investigated privacy protection schemes for speaker recognition applications. The paper entitled „Preserving privacy in speech and speech characterization“, was worked out as part an extensive and interdisciplinary collaboration
Prof. Alice J. O’Toole from the University of Texas at Dallas delivered a Distinguished Lecture on Deep Learning and CNN at CRISP, Germany on June 3rd. The lecture entitled: „Turning a face recognition black box white: Understanding what deep convolutional
The objective of European Training Networks (ETN) is the structured training of highly skilled early-stage researchers in excellent research projects. More information: https://ec.europa.eu/research/mariecurieactions/actions/get-funding/innovative-training-networks_en
Hendrik Schneider verteidigt am 08.05.2019 erfolgreich seine Masterarbeit mit dem Titel „Hauptspeicherprofiling einer virtuellen Windows Maschine mittels DRAKVUF“. Die Arbeit diskutiert die mögliche Erweiterung eines Malware-Analyse-Systems um eine Komponente zur automatisierten Extraktion von gepackten Executables.
This work discusses a comprehensive amount of anti-forensic techniques and introduces classifications. These techniques are already covering a wide range of fields. But they either do this only partially or are proprietary solutions. In contrast to these proprietary techniques we
Marta Gomez-Barrero held a seminar on Biometric Template Protection and Evaluation during the biometrics and cryptography seminar series taking place at COSIC, KU Leuven, in the Winter / Spring Season 2019. The contents can be summarised as follows: The recent discussion
Lorenz Liebler of the da/sec group received a best student paper award for the contribution of „Towards Exact and Inexact Approximate Matching of Executable Binaries“ at the 2019 DFRWS-EU in Oslo, Norway. Abstract: The application of approximate matching (a.k.a. fuzzy
Henrik Kawa defended his Master Thesis on Homomorphic Encryption for Fingerprint Verification Biometric data is unique to each individual and according to EU’s General Data Protection Regulation (GDPR), it classifies as sensitive data. Since it is classified as sensitive data, there