PhD Security and Privacy of/with Neuromorphic Computing Devices (1,0 FTE)

rug university groningen
  • Groningen
  • University of Groningen
Posted on

Inspired from how the human-brain works, neuromorphic computing has the promise that many of the AI tasks can be performed in orders of magnitude more efficiently in terms of energy consumption and computational requirements than the current AI solutions. At the same time, side channel attacks, exploitation of any other information (e.g., power consumption, electromagnetic/acoustic emissions, timing of computation) than the design/algorithm flaw of the system itself, are on the rise as it has been seen with Spectre and Meltdown vulnerabilities in 2017.

In this cross-disciplinary CogniGron project, we aim to investigate the security of neuromorphic chips against side channel attacks and their suitability for implementing security-critical functionality. Starting the investigation at the level of circuits, our particular focus will be on memristor-based designs (and the commonly used materials in their construction), their security relevant properties (e.g., stochasticity and indistinguishability) and some of the high level choices during their design/usage. After identifying/selecting the most relevant side channel attacks based on the available emissions, we will first study whether the selected (memristor-based) neuromorphic circuits are vulnerable against them. We will then focus on a use case in which memristors constructed with different materials are used to implement Physically Uncloneable Functions (PUF), which are expected to proliferate due to the increased number of IoT deployments. Depending on the availability of the time, we also plan to evaluate our findings at a higher level where memristors are used to implement more sophisticated AI functionality, i.e., spiking neural networks.

The objective of the temporary position is the production of a number of research articles in peer-reviewed scientific journals and conference proceedings, which together will form the basis of a thesis leading to a PhD degree (Dr) at the University of Groningen.

Founded in 1614, the University of Groningen enjoys an international reputation as a dynamic and innovative institution of higher education offering high-quality teaching and research. Flexible study programmes and academic career opportunities in a wide variety of disciplines encourage the 35,000 students and researchers alike to develop their own individual talents. As one of the best research universities in Europe, the University of Groningen has joined forces with other top universities and networks worldwide to become a truly global centre of knowledge.

Within the Faculty of Science and Engineering, a 4-years PhD position is available at the Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence with the topic of security of neuromorphic computing and neuromorphic computing for security. The candidate would become a member of the Information Systems Group of the Computer Science Department and will work under the supervision of Dr Fatih Turkmen.

Ole Gmelin

"Speaking Dutch in the Netherlands will always open certain doors for you when it comes to finding a job. But, it isn’t always a must."

Will you become our new PhD Security and Privacy of/with Neuromorphic Computing Devices (1,0 FTE)? Apply at University of Groningen