We held our next tinyML Talks webcast. Manuel Brosch and Matthias Probst from Technical University Munich (TUM) have presented Security of Edge AI against Hardware Attacks on January 13, 2021.
Neural networks are widespread in usage and are amenable to many applications. However, depending on the task a network should perform, training can be compute and time consuming. Consequently, in many cases a neural network is an intellectual property worthwhile to protect. A possible attack target is to reverse engineer the network and build a copy of it. In the domain of edge AI, hardware attacks like side-channel analysis must be considered, since an attacker may get physical access to the device.
Matthias Probst finished his bachelor’s degree in electronics and computer science at Munich University of Applied Sciences in 2017. In 2020, he completed his master degree at Technical University Munich (TUM) in electronics and computer science. Since April 2020 he is working as research associate at the Chair of Security in Information Technology at TUM. His research area is the security of spiking neural network accelerators against hardware attacks and especially side-channel analysis.
Manuel Brosch received his bachelor’s degree in computer engineering from Esslingen University of Applied Sciences. From Technical University Munich he received in 2019 his master’s degree in electrical engineering and computer science. He is working as a research associate at the Chair of Security in Information Technology at the Technical University Munich, since April 2020. His research area is the security of neural networks running on edge devices against hardware attacks, such as side-channel analysis.
==========================
Watch on YouTube:
Manuel Brosch and Matthias Probst
Download presentation slide:
Manuel Brosch and Matthias Probst
Feel free to ask your questions on this thread and keep the conversation going!