In this work we present SCRAMBLE, a configurable neuromorphic architecture that provides security against different threats by employing memristors for critical parts and functions. More specifically, we employ memristive memory cells - that are 3D stacked on top of the configurable neuromorphic hardware - to securely hold the weights as well as activation functions of any model processed on the generalized architecture. Thus, programmable memristive cells enable reconfiguration of the architecture to thwart both model stealing and hardware IP stealing attacks. We implement a proof-of-concept for the proposed architecture and analyze its security metrics. We also benchmark it against selected prior art for neuromorphic architectures to quantify the security-performance trade-offs.

@en

The traditional Von-Neumann architecture is reaching its limits and finding it difficult to cope up with the ever-increasing demands of modern workloads like artificial intelligence. This demand has fueled the search of technologies that can mimic human brain to efficiently combine both memory and computation within a single device. In this work, we present the state-of-the-art research in the domain of computation-in-memory. In particular, we take a look at memristors and its widespread application in neuromorphic computation. We introduce ReRAMs in terms of their novel computing paradigms and present ReRAM-specific design flows. We address the various circuit opportunities and challenges related to reliability and fault tolerance associated with them. Another high-potential candidate to leverage memory and computation from a single device is Ferroelectric Field-effect Transistor (FeFET). Here we present a co-integration of such FeFETs with another emerging nanotechnology concept, called Reconfigurable Field Effect Transistor (RFET) and discuss the impact of the higher amount of states provided by this combination.@en