Computation offloading of a vehicle’s continuous intrusion detection workload for energy efficiency and performance

Abstract

Computation offloading has been used and studied extensively in relation to mobile devices. That is because their relatively limited processing power and reliance on a battery render the concept of offloading any processing/energy-hungry tasks to a remote server, cloudlet or cloud infrastructure particularly attractive. However, the mobile device's tasks that are typically offloaded are not time-critical and tend to be one-off. We argue that the concept can be practical also for continuous tasks run on more powerful cyber-physical systems where timeliness is a priority. As case study, we use the process of real-time intrusion detection on a robotic vehicle. Typically, such detection would employ lightweight statistical learning techniques that can run onboard the vehicle without severely affecting its energy consumption. We show that by offloading this task to a remote server, we can utilse approaches of much greater complexity and detection strength based on deep learning. We show both mathematically and experimentally that this allows not only greater detection accuracy, but also significant energy savings, which improve the operational autonomy of the vehicle. In addition, the overall detection latency is reduced in most of our experiments. This can be very important for vehicles and other cyber-physical systems where cyber attacks can directly affect physical safety. In fact, in some cases, the reduction in detection latency thanks to offloading is not only beneficial but necessary. An example is when detection latency onboard the vehicle would be higher than the detection period, and as a result a detection run cannot complete before the next one is scheduled, increasingly delaying consecutive detection decisions. Offloading to a remote server is an effective and energy-efficient solution to this problem too.

An Overview of Automotive Service-Oriented Architectures and Implications for Security Countermeasures

“…Additionally, the E/E architecture of the future will not end at the vehicles external borders, but spans to the backend systems that can also provide services to the vehicle. Thus, offloading a vehicles security computations may be a feasible option (e.g., [96], [97]). Furthermore, from a technological perspective more efficient access controls with revocation capabilities, intelligent IDS features for encrypted traffic or high-throughput firewalls for sensory data are an open topic for research.…”

A taxonomy and survey of cyber-physical intrusion detection approaches for vehicles

“…In vehicular networks, where there is the opportunity for multiple vehicles to collaborate with each other, the data collection and processing can be shared between them and the detection decisions can be taken in a distributed manner. Where the vehicle itself is not powerful enough to perform meaningful IDS onboard and there is no opportunity for collaboration with other vehicles, then the IDS can be run externally, for example by the computing system of a human operator controlling the vehicle remotely or by offloading the IDS processing to a remote cloud infrastructure [13].…”

“…3) Offloaded detection: If being able to self-detect threats is not a requirement and collaboration with neighbouring nodes is not an option, then it may be efficient to offload the detection process onto a remote service ( Figure 5), as in [13]. A key benefit is that access to a more powerful system (e.g., a cloud) means access to more powerful algorithms for intrusion detection, for example based on deep learning, which may otherwise be prohibitive for a resource-constrained vehicle.…”

“…However, in terms of the origin of a sensor's failure, there is no provision to distinguish between malicious threats of cyber origin and natural sensor failures, making this work rather impractical in this context. Contrary to previous approaches that prioritise lightweight approaches, Loukas et al [13], [67] have shown that very accurate, but also computationally heavy machine learning algorithms, such as deep learning, can be used if the detection task is offloaded to a more powerful infrastructure, such as a remote server or cloud. The authors argue that computation offloading can be extremely useful for demanding, realtime and continuous tasks required by resource-constrained and time-critical cyber-physical systems.…”

Improved Deep Belief Networks (IDBN) Dynamic Model-Based Detection and Mitigation for Targeted Attacks on Heavy-Duty Robots

“…Loukas et al [13] proposed a real-time detection system that used lightweight statistical learning techniques, which used approaches of much greater complexity and detection strength based on deep learning to improve detection accuracy and save energy. Bezemskij et al [14] proposed a method based on Bayesian networks, which could not only determine whether a robot was attacked, but also determine whether the attack came from the cyber-domain or the physical-domain.…”