Graph-based detection for false data injection attacks in power grid

Li, Xueping; Wang, Yaokun; Lu, Zhigang

doi:10.1016/j.energy.2022.125865

Cited by 20 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[81] proposed a spatiotemporal DL network for FDIA detection in AC-model power grids. As previous works did not consider power grid topology changes, [77] considered the FDIA issue under topology dynamics using a gated GNN and graph attention network-based model for detection.…”

Section: Classification Literaturementioning

confidence: 99%

“…Using deep learning as auxiliaries [52,66,72,74] Simply developing classifiers for detection [53,54,69,76,77,81] Locating false data injection attacks [55,56,60,63,68,75] Resorting to deep reinforcement learning for detection [64,65,79,95] Detecting attacks with specific targets [57,70,78,80] Addressing the problem of attack samples insufficiency [58,59,67,83] Considering disturbances from renewable energy integration [60,61] Handling the privacy problem in constructing detectors [62,71,73] [51] designed novel FDIA strategies by introducing adversarial samples (also called perturbation vectors) into FDIAs, thereby deceiving BDDs and DL-based detectors.…”

Section: Classification Literaturementioning

confidence: 99%

See 1 more Smart Citation

Deep learning for cybersecurity in smart grids: Review and perspectives

Ruan

Liang

Zhao

et al. 2023

Energy Conversion and Econom

View full text Add to dashboard Cite

Protecting cybersecurity is a non‐negotiable task for smart grids (SG) and has garnered significant attention in recent years. The application of artificial intelligence (AI), particularly deep learning (DL), holds great promise for enhancing the cybersecurity of SG. Nevertheless, previous surveys and review articles have failed to comprehensively investigate the intersection between DL and SG cybersecurity. To address this gap, this study presents a survey of the latest advancements in DL technology and their relevance to SG cybersecurity. First, the functional mechanisms and scope of application of common DL techniques are explored. Subsequently, SG cyberthreats are categorised into distinct types of cyberattacks that have not been systematically examined in previous surveys. Based on this, a thorough review of the application of DL techniques in addressing each cyberthreat along with recommendations and a generalised framework for enhancing cyberattack detection using DL is offered. Finally, insights are provided into the emerging challenges presented by DL applications in SG cybersecurity that are yet to be widely acknowledged, and potential research avenues are proposed to address or alleviate these challenges.

show abstract

Section: Classification Literaturementioning

confidence: 99%

Section: Classification Literaturementioning

confidence: 99%

Deep learning for cybersecurity in smart grids: Review and perspectives

Ruan

Liang

Zhao

et al. 2023

Energy Conversion and Econom

View full text Add to dashboard Cite

show abstract

“…Thus, much effort should be devoted to investigating FDI attacks therein. Many interesting works have been conducted in recent years, including attack detection [35][36][37][38][39], resilient control strategies [40][41][42][43], and survey articles [15,44,45]. The following are some representative works on this subject since this subsection is not the primary focus; for more details, one may refer to the specialized survey paper on this topic listed above.…”

Section: False Data Injection (Fdi) Attackmentioning

confidence: 99%

“…The feedback mechanism, which utilizes a dynamic time-wrapping distance, was designed to handle delayed communication and varying attack signals. In [39], the authors designed a FDI detection approach relying on a graph neural network that considers changes in a power grid architecture. Using a gated graph neural network (GGNN), the approach collects spatial information from both the power grid structure and operational data.…”

Section: False Data Injection (Fdi) Attackmentioning

confidence: 99%

A Brief Survey of Recent Advances and Methodologies for the Security Control of Complex Cyber–Physical Networks

Wan

Alsaedi

2023

Sensors

View full text Add to dashboard Cite

Complex cyber–physical networks combine the prominent features of complex networks and cyber–physical systems (CPSs), and the interconnections between the cyber layer and physical layer usually pose significant impacts on its normal operation. Many vital infrastructures, such as electrical power grids, can be effectively modeled as complex cyber–physical networks. Given the growing importance of complex cyber–physical networks, the issue of their cybersecurity has become a significant concern in both industry and academic fields. This survey is focused on some recent developments and methodologies for secure control of complex cyber–physical networks. Besides the single type of cyberattack, hybrid cyberattacks are also surveyed. The examination encompasses both cyber-only hybrid attacks and coordinated cyber–physical attacks that leverage the strengths of both physical and cyber attacks. Then, special focus will be paid to proactive secure control. Reviewing existing defense strategies from topology and control perspectives aims to proactively enhance security. The topological design allows the defender to resist potential attacks in advance, while the reconstruction process can aid in reasonable and practical recovery from unavoidable attacks. In addition, the defense can adopt active switching-based control and moving target defense strategies to reduce stealthiness, increase the cost of attacks, and limit the attack impacts. Finally, conclusions are drawn and some potential research topics are suggested.

show abstract

“…To prevent these issues, power grid operators adopt advanced monitoring systems to examine the grid performance in real time [ 4 , 5 ]. These systems collect data from sensors and other devices installed throughout the grid and employ sophisticated analytics to detect any anomalies or potential problems [ 6 , 7 ]. Therefore, thanks to early identification, grid operators can take corrective actions to avert power outages and ensure the reliability and stability of the grid.…”

Section: Introductionmentioning

confidence: 99%

Validation of a Simplified Method for Estimating the Harmonic Response of Rogowski Coils with the Monte Carlo Method

Betti,

Mingotti,

Tinarelli

et al. 2024

Sensors

View full text Add to dashboard Cite

The need to monitor the power network is leading to a significant increase in the number of measurement points. These points consist of intelligent electronic devices and instrument transformers (or more in general sensors). However, as the number of devices increases, so does the demand for their characterization and testing. To this end, the authors formulated a new characterization procedure that offers numerous benefits for manufacturers and system operators. These benefits include: (i) reducing testing time (thus lowering costs), (ii) simplifying the existing procedures, and (iii) increasing the number of tested devices. In this study, to complete the validation of the proposed characterization procedure, the authors performed a comprehensive uncertainty evaluation. This included the identification and analysis of the uncertainty sources, the implementation of the Monte Carlo method to obtain the statistical parameters of the quantities of interest, and the final method assessment according to the obtained results. Each step is described in detail, and the results allow one to (i) replicate the uncertainty analysis on other types of instrument transformers and (ii) implement the proposed harmonic characterization procedure with the confidence that the method is accurate, flexible, and scalable.

show abstract

Graph-based detection for false data injection attacks in power grid

Cited by 20 publications

References 34 publications

Deep learning for cybersecurity in smart grids: Review and perspectives

Deep learning for cybersecurity in smart grids: Review and perspectives

A Brief Survey of Recent Advances and Methodologies for the Security Control of Complex Cyber–Physical Networks

Validation of a Simplified Method for Estimating the Harmonic Response of Rogowski Coils with the Monte Carlo Method

Contact Info

Product

Resources

About