The introduction of deep learning (DL) technology can improve the performance cyber–physical systems (CPSs) in many ways. However, this also brings new security issues. To tackle these challenges, article explores vulnerabilities DL-based unmanned aerial vehicles (UAVs), which are typical CPSs. Although research works have been reported previously on adversarial attacks DL models, only few them concerned about safety-critical CPSs, especially regression models such systems. In article, we...

Deep learning methods can not only detect false data injection attacks (FDIA) but also locate of FDIA. Although adversarial (AFDIA) based on deep vulnerabilities have been studied in the field single-label FDIA detection, attack and defense against multi-label locational detection are still involved. To bridge this gap, paper first explores example detectors proposes a general framework, namely muLti-labEl adverSarial falSe injectiON (LESSON). The proposed LESSON framework includes three key...

Although state estimation using a bad data detector (BDD) is key procedure employed in power systems, the vulnerable to false injection attacks (FDIAs). Substantial deep learning methods have been proposed detect such attacks. However, neural networks are susceptible adversarial or examples, where slight changes inputs may lead sharp corresponding outputs even well-trained networks. This article introduces joint example and FDIAs (AFDIAs) explore various attack scenarios for systems....

Vulnerability of various machine learning methods to adversarial examples has been recently explored in the literature. Power systems which use these vulnerable face a huge threat against examples. To this end, we first propose signal-specific method and universal signal-agnostic attack power using generated Second, black-box attacks based on transferable characteristics above two are also proposed evaluated. Third, training is adopted defend attacks. Experimental analyses demonstrate that...

State estimation methods used in cyber–physical systems (CPSs), such as smart grid, are vulnerable to false data injection attacks (FDIAs). Although substantial deep learning have been proposed detect attacks, neural networks (DNNs) highly susceptible adversarial which modify input of DNNs with unnoticeable but malicious perturbations. This article proposes a method explore targeted and stealthy FDIAs via machine learning. We pose sparse optimization problems achieve initial attack...

Summary The smart grid faces a variety of physical and cyber attacks. Coordinated cyber‐physical attacks can cause severer consequences than the single or attacks, which be divided into two categories according to whether attack is stealthy not. considering DoS are investigated due lower cost In each category coordinated mathematical models derived suitable methods adopted solve corresponding issue. experimental simulation demonstrates potentially damaging effects threats this newly proposed...

Reconfigurable intelligent surface (RIS) enables performance enhancement of communication networks due to its significant reflective gain, which could also be used strengthen secure transmission. In this paper, we consider a RIS enabled unmanned aerial vehicle (UAV) network, in the UAV serves as base station for terrestrial legitimate user accompanied by eavesdropper. Specifically, security considered network is enhanced under both instantaneous and statistical eavesdropper channel state...

Beamforming is a promising technique to enhance the security of wireless transmission, while optimal beamforming design with partial channel state informing (CSI) challenging. This letter develops three-dimensional (3D) robust method for unmanned aerial vehicle (UAV) communication systems in physical layer perspective. Specifically, aiming at maximizing average secrecy rate considered system, precisely designed neural network trained optimize beamformer confidential signal and artificial...

In view of the scarce spectrum resources and inconvenient deployment in wireless communications, this work focuses on an unmanned aerial vehicle (UAV) enabled non-orthogonal multiple access (NOMA) system where a UAV deployed as base station serves two users by NOMA. A joint power allocation jamming (PAAJ) scheme is proposed to achieve reliable secure communications for presence malicious eavesdropper. To be specific, dynamic adopted ensure reliability another friendly jammer introduced...

This paper investigates the green and secure communications of multi-UAV NOMA systems. A joint energy transfer artificial noise (ETAN) scheme is proposed to enhance endurance secrecy performance system. In particular, communication can be divided into two phases during each time frame. first phase, system harvests from a power beacon. second UAVs perform transmit confidential messages uplink base station in presence eavesdropping UAVs. Simultaneously, safeguard system, beacon transmits...

In this letter, the unitary matrix pencil (UMP) method is utilized for shaped-beam pattern synthesis of maximally sparse linear arrays. Taking advantage equivalent obtained by a transformation, UMP-based constructs novel relation between element positions and generalized eigenvalues, which contributes to real solutions all thereby improves matching accuracy patterns. addition, complex computations in both singular value decomposition eigenvalue procedures are converted into ones through...

This article explores the problem of protection against false data injection attacks (FDIAs) on power system state estimation. Although many research works have been reported previously to solve same problem, yet most them are only for perfect FDIAs. To address reasonably, all related factors influencing success probability and corresponding attack impact imperfect FDIAs should also be considered. Based such considerations, a topology, parameter, accuracy, level (TOTAL) strategy considering...

Abstract Deep learning has been recently used in safety‐critical cyber‐physical systems (CPS) such as the smart grid. The security assessment of learning‐based methods within CPS algorithms, however, is still an open problem. Despite existing research on adversarial attacks against deep models, only few works are concerned about energy CPS, especially state estimation routine. This paper investigates issues neural network based Specifically, problem analysed and efficient attack method...

Intelligent reflecting surface (IRS)-assisted wireless communication has been recognized as an important way to enhance the security of unmanned aerial vehicle (UAV) networks. However, a single IRS may be unable meet transmission requirements in complex scenarios. In particular, due inherent instability UAV platforms, inevitable jitter caused by airflow and body vibration can have great impact on quality. this paper, we study multi-aerial (AIRS) assisted secure simultaneous information power...

Recent researches on data-driven and low-sparsity data injection attacks have been presented, respectively. To combine the two main goals (data-driven low-sparsity) of research, this paper presents a false attack strategy. The proposed attacking strategy (EID: Eliminate-Infer-Determine) is divided into three stages. In first step, intercepted preprocessed by sparse optimization techniques to eliminate outliers. recovered then exploited learn about system matrix based parallel factorization...

The purpose of this paper is to outline and summarize the latest technology on UAV security. This driven by growing market share represented technology. A silent yet vital revolution happening: UAVs are becoming cheaper more widely used. Unfortunately, security safety aspects were overlooked manufacturers who eliminated potential threats considered small as toys. To demonstrate importance once again, real examples vulnerabilities dangerous attacks shown.

Reconfigurable intelligent surface (RIS) is viewed as a promising technique that can be utilized to improve the performance of systems by reconfiguring signal propagation environments. This article investigates green and secure unmanned aerial vehicle (UAV) Internet Things (IoT) communications with aid RIS, where multiple UAVs harvest energy from power beacon (PB) send information uplink access point (AP) nonorthogonal (NOMA). In particular, communication divided into two phases during each...

An innovative technique based on the enhanced unitary matrix pencil (MP) method is presented for design of sparse multiple-pattern linear arrays. By virtue equivalent MP obtained with a transformation, relation between element positions and generalized eigenvalues achieved in this method, which contributes to real solutions common all multiple patterns. Owing utilization transformation that can convert complex one, computational complexity be significantly reduced since only computations are...