Machine learning, big-data and internet-of-things are some of the emerging computing applications which are extremely demanding in terms of storage, energy and performance. While conventional von Neumann architectures are facing significant challenges to cope with such demands, computing-in-memory architectures in general and neuro-inspired architectures, in particular, represent a promising solution to overcome these limitations.
This Master/Bachelor Thesis aims to investigate novel Hardware Security vulnerabilities and their countermeasure of neuromorphic computing architecture. In particular, the student will have the unique opportunity to work with the real ReRAM crossbars to perform measurements within our labs.
Among others, these steps must be done:
- Literature research about hardware attacks
- Circuit simulation of the attack
- Experiment with real-world ReRAM cells to verify the attack
- Design and implementation of a countermeasure to mitigate the attack
- Evaluation and verification