Deep Learning-based Intrusion Detection System for Electric Vehicle Charging Station

Basnet, Manoj; Ali, Mohd. Hasan

doi:10.1109/spies48661.2020.9243152

Cited by 40 publications

(25 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The communication system is the nerves of the EVSE that facilitates various operations such as EV scheduling, slot allotment, authentication and authorization, charging session control, grid integration, and on and on [11]. Therefore, once the communication is compromised, the entire EVSE is at the risk of disruption and dismantling.…”

Section: Cybersecurity Issues In Evsementioning

confidence: 99%

“…The more sophisticated and stealthy attack can be launched without being caught but the impact may not be enough to disrupt the normal operation. The stealthy false data xa can be estimated using some nonlinear functions g as Equation (12) with the help of Equation (11). Now the stealthy attack's objective is to get the attack vector a that maximizes the error injected into the system without exceeding the detection threshold of 𝜏 which is the constrained optimization problem as in Equation (13).…”

Section: Fdi Attack Modellingmentioning

confidence: 99%

“…It helps the operator take protective and preventive measures once the attack is identified. There are three types of IDS derived from their implementation locations, namely: Host-based (HIDS), network-based (NIDS), and hybrid IDS [11]. Three basic intrusion detection techniques have been widely deployed in state-of-the-art applications, namely: Signature-based detection (SD), Anomaly based detection (AD), and Stateful protocol analysis (SPA) [11,16].…”

Section: Introductionmentioning

confidence: 99%

“…The proposed IDS implements the variant of recurrent neural network (RNN) called stacked or deep LSTM specifically designed to deal with sequential learning. The motivation for using LSTM came from the sequential nature of electrical and control signals and its superior classification performance in our past work [11]. Unlike current work, our past work solely depended on network packet fingerprint to train the deep learning models to detect the cyberattacks at the network layer.…”

Section: Introductionmentioning

confidence: 99%

“…The communication vulnerabilities can be exploited to get access to the SCADA or EVSE system.An attacker may use social engineering such as phishing and/or reverse engineering to get the legitimate SCADA's or EV's credentials. Then, the attacker can impersonate the legitimate SCADA operator or EV owner to breach the system security[11].…”

mentioning

confidence: 99%

See 4 more Smart Citations

Exploring cybersecurity issues in 5G enabled electric vehicle charging station with deep learning

Basnet

Ali

2021

IET Generation Trans & Dist

Self Cite

View full text Add to dashboard Cite

The surging usage of electric vehicles (EVs) demand the robust deployment of trustworthy electric vehicle charging station (EVCS) with millisecond range latency and massive machine to machine communications where 5G could act. However, 5G suffers from inherent protocols, hardware, and software vulnerabilities that seriously threaten the communicating entities' cyber-physical security. To overcome these limitations in the EVCS system, this paper analyses the impact of False Data Injection (FDI) and Distributed Denial of Services (DDoS) attacks on the operation of EVCS. This work is an extension of the previously published conference paper about the EVCS. As new features, this paper simulates the FDI attack and the syn flood DDoS attacks on 5G enabled remote Supervisory Control and Data Acquisition (SCADA) system that controls the solar photovoltaics (PV) controller, Battery Energy Storage (BES) controller, and EV controller of the EVCS. The extent of delay has been increased to more than 500 ms with the severe DDoS attack via 5G. The attacks make the EVCS system oscillate or shift the DC operating point. The frequency of oscillation, its damping, and the system's resiliency are found to be related to the attacks' intensity and the target controller. Finally, the novel stacked Long Short-Term Memory (LSTM) based intrusion detection systems (IDS) are proposed solely based on the electrical fingerprint. This model can detect the stealthy cyberattacks that bypass the cyber layer and go unnoticed in the monitoring system with nearly 100% detection accuracy.

show abstract

Section: Cybersecurity Issues In Evsementioning

confidence: 99%