A new methodology for anomaly detection of attacks in IEC 61850-based substation system

Yang, Liqun; Zhai, Yikui; Zhang, Yipeng; Zhao, Yufei; Li, Zhoujun; Xu, Tongge

doi:10.1016/j.jisa.2022.103262

Cited by 5 publications

(1 citation statement)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 17 , authors presented a sliding window-based sequential classification mechanism to detect abnormalities. Similarly, in 18 , discrete wavelet transform (DWT) and Long Short-Term Memory (LSTM)-based autoencoder network is proposed to detect anomalies in GOOSE messages.…”

Section: Introductionmentioning

confidence: 99%

A novel hybrid methodology to secure GOOSE messages against cyberattacks in smart grids

Hussain

Iqbal

Zanero

et al. 2023

Sci Rep

View full text Add to dashboard Cite

IEC 61850 is emerging as a popular communication standard for smart grids. Standardized communication in smart grids has an unwanted consequence of higher vulnerability to cyber-attacks. Attackers exploit the standardized semantics of the communication protocols to launch different types of attacks such as false data injection (FDI) attacks. Hence, there is a need to develop a cybersecurity testbed and novel mitigation strategies to study the impact of attacks and mitigate them. This paper presents a testbed and methodology to simulate FDI attacks on IEC 61850 standard compliant Generic Object-Oriented Substation Events (GOOSE) protocol using real time digital simulator (RTDS) together with open-source tools such as Snort and Wireshark. Furthermore, a novel hybrid cybersecurity solution by the name of sequence content resolver is proposed to counter such attacks on the GOOSE protocol in smart grids. Utilizing the developed testbed FDI attacks in the form of replay and masquerade attacks on are launched and the impact of attacks on electrical side is studied. Finally, the proposed hybrid cybersecurity solution is implemented with the developed testbed and its effectiveness is demonstrated.

show abstract

Section: Introductionmentioning

confidence: 99%