About
I am currently a Machine Learning Researcher at the Huawei Munich Research Center.
Before that, I completed my PhD at the University of Oxford, funded by an Oxford-Deepmind scholarship. In my dissertation - titled Measuring the Security of Computer Vision Systems to Adversarial Attacks - I studied adversarial examples for deep neural networks and how to evaluate the security of systems based on sensors-perception, with the goal of finding sounder ways to evaluate and improve machine learning robustness.
During my PhD, I was lucky enough to collaborate with industrial partners, including Mastercard, the armasuisse Cyber-Defence Campus, and to intern at the Bosch Center for Artificial Intelligence Research, where I investigated properties of Transformer-based networks for vision tasks under the supervision of Jan Hendrik Metzen.
Recent Work
G. Lovisotto, N. Finnie, M. Munoz, C.K. Mummadi and J.H. Metzen
Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustness
CVPR 2022
paper
H. Turner, G. Lovisotto and I. Martinovic
Speaker Anonymization with Distribution-Preserving X-Vector Generation
2020 VoicePrivacy Challenge
paper
code
Henry's talk
S. Eberz, G. Lovisotto, K. B. Rasmussen, V. Lenders and I. Martinovic
28 Blinks Later: Tackling Practical Challenges of Eye Movement
Biometrics
2019 ACM CCS
paper
S. Eberz, G. Lovisotto, A. Patane, M. Kwiatkowska, V. Lenders and I. Martinovic
When your fitness tracker betrays you: Quantifying the
predictability of biometric features across contexts
2018 IEEE S&P
paper