Real-time Adaptive Sensor Attack Detection and Recovery in Autonomous Cyber-physical Systems

<p>Cyber-Physical Systems (CPS) tightly couple information technology with physical processes, which rises new vulnerabilities such as physical attacks that are beyond conventional cyber attacks.Attackers may non-invasively compromise sensors and spoof the controller to perform unsafe actions. This issue is even emphasized with the increasing autonomy in CPS. While this fact has motivated many defense mechanisms against sensor attacks, a clear vision of the timing and usability (or the false alarm rate) of attack detection still remains elusive. Existing works tend to pursue an unachievable goal of minimizing the detection delay and false alarm rate at the same time, while there is a clear trade-off between the two metrics. Instead, this dissertation argues that attack detection should bias different metrics (detection delay and false alarm) when a system sits in different states. For example, if the system is close to unsafe states, reducing the detection delay is preferable to lowering the false alarm rate, and vice versa. This dissertation proposes two real-time adaptive sensor attack detection frameworks. The frameworks can dynamically adapt the detection delay and false alarm rate so as to meet a detection deadline and improve usability according to different system statuses. We design and implement the proposed frameworks and validate them using realistic sensor data of automotive CPS to demonstrate its efficiency and efficacy.</p><p>Further, this dissertation proposes \textit{Recovery-by-Learning}, a data-driven attack recovery framework that restores CPS from sensor attacks. The importance of attack recovery is emphasized by the need to mitigate the attack's impact on a system and restore it to continue functioning. We propose a double sliding window-based checkpointing protocol to remove compromised data and keep trustful data for state estimation.</p><p>Together, the proposed solutions enable a holistic attack resilient solution for automotive cyber-physical systems.</p>

Name thesis:degree_name

Doctor of Philosophy (PhD)

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Electrical Engineering and Computer Science

Year

2021

Author dc:creator

• Akowuah, Francis

Contributors dc:contributor

• Kong, Fanxin
• Moon, Young B.

• attack detection
• attack recovery
• cyber-physical security
• sensor attack resiliency
• Computer Sciences
• Physical Sciences and Mathematics

Repository record dc:identifier

https://surface.syr.edu/etd/1359

OAI identifier oai:identifier

oai:surface.syr.edu:etd-2360