Privacy-Preserving Resilience of Cyber-Physical Systems to Adversaries

Ramasubramanian, Bhaskar; Niu, Luyao; Clark, Andrew; Bushnell, Linda; Poovendran, Radha

doi:10.1109/cdc42340.2020.9304080

Cited by 7 publications

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Integration of UAVs with AI, IoT, and wireless networks has increased their vulnerability to cyberattacks. 89,[125][126][127][128][129] Possible cyber-attacks to be tackled by a UAV communication network are message forgery, path variation, data modification, GPS spoofing, UAV spoofing, UAV hijack, virus and malware attack, DDoS attacks, jamming, and routing attacks. 125 Countermeasures are taken through the deployment of intrusion detection systems (IDSs).…”

Section: Networked Uavs and Cyber-attacksmentioning

confidence: 99%

Unmanned aerial vehicles: Applications, techniques, and challenges as aerial base stations

Rolly

Malarvezhi

Λάγκας

2022

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Next generation wireless networks are expected to be greatly supported by unmanned aerial vehicles, which can act as aerial base stations and constitute a promising solution for the exorbitant rise in user demands. This is possible because of unmanned aerial vehicle characteristics such as mobility, flexibility, increased line-of-sight probability, and their ability to access unreachable locations. Extensive research is now widely performed on the deployment, performance analysis, resource management, trajectory optimization, and channel modeling in such networks. This survey article focuses on the different applications and the related algorithms for realizing aerial base stations by thoroughly reviewing each related research area. In a nutshell, this article provides key applications, challenges, and the technology used for the design and analysis of unmanned aerial vehicles as base stations.

show abstract

Section: Networked Uavs and Cyber-attacksmentioning

confidence: 99%

Unmanned aerial vehicles: Applications, techniques, and challenges as aerial base stations

Rolly

Malarvezhi

Λάγκας

2022

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

show abstract

“…An overview of results that use differential privacy in control is presented in the survey [44]. A characterization of differential privacy for discrete-state Markov chains was presented in [45], and this was extended to trajectories of discrete MDPs in our previous work [46]. Algorithmic guarantees on the differential privacy of policies in RL using Monte-Carlo techniques were provided in [47].…”

Section: Related Workmentioning

confidence: 99%

Privacy-Preserving Reinforcement Learning Beyond Expectation

Rajabi¹,

Ramasubramanian²,

Maruf³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Cyber and cyber-physical systems equipped with machine learning algorithms such as autonomous cars share environments with humans. In such a setting, it is important to align system (or agent) behaviors with the preferences of one or more human users. We consider the case when an agent has to learn behaviors in an unknown environment. Our goal is to capture two defining characteristics of humans: i) a tendency to assess and quantify risk, and ii) a desire to keep decision making hidden from external parties. We incorporate cumulative prospect theory (CPT) into the objective of a reinforcement learning (RL) problem for the former. For the latter, we use differential privacy. We design an algorithm to enable an RL agent to learn policies to maximize a CPT-based objective in a privacy-preserving manner and establish guarantees on the privacy of value functions learned by the algorithm when rewards are sufficiently close. This is accomplished through adding a calibrated noise using a Gaussian process mechanism at each step. Through empirical evaluations, we highlight a privacy-utility tradeoff and demonstrate that the RL agent is able to learn behaviors that are aligned with that of a human user in the same environment in a privacy-preserving manner.

show abstract