CHASE: A Configurable Hardware-Assisted Security Extension for Real-Time Systems

Real-time autonomous systems are becoming pervasive in many application domains such as vehicular ad-hoc networks, smart factories and delivery drones. The correct functioning of these real-time systems is timing-critical with hard deadlines. However, although they interact with other systems and exchange inputs/outputs with the physical world, they usually lack security mechanisms, which makes them susceptible to a wide range of attacks with critical consequences. Typically, this is because security mechanisms usually violate the real-time requirements of these systems and cannot be adjusted at runtime to provide the adequate security without compromising performance. In this paper, we propose a consolidated runtime-configurable hardware-assisted security extension called CHASE that supports different levels of security at runtime. Depending on the desired security level and the system real-time, availability or functionality requirements, CHASE can be configured accordingly at runtime, thus enabling the calibration of the security vs. performance trade-off. We analyze CHASE's effectiveness in providing different security guarantees against various adversarial capabilities, and show how this is achieved with reasonable logic overhead and minimal performance overhead.

I. Introduction

Real-time systems are ubiquitous in many application domains such as programmable logic controllers (PLCs), electronic control units (ECUs) and emerging domains that deploy networks of collaborative autonomous systems, e.g., vehicular ad-hoc networks, smart factories, search and rescue, and delivery robots and drones. Typically, such systems are required to perform their tasks in real time, while some may have hard and critical time deadlines with little tolerance for down time. They may also be deployed in safety-critical or non-deterministic infrastructures where their fail-safe operation is paramount. To perform their tasks, they might also be interconnected with the physical world and other devices, making them equally vulnerable as other systems to security exploits.