Detection of Denial of Service Attacks Using Echo State Networks

Bekshentayeva, Kamila; Trajković, Ljiljana

doi:10.1109/smc52423.2021.9659212

Cited by 3 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reservoir computing (RC), as an emerging and promising paradigm in the realm of RNNs, inherits the ability to process temporal data while getting rid of gradient descent-based training methods, thereby alleviating the computational burden and accelerating convergence speed. Reference [17] utilized echo state network, a type of RC, to discriminate attacks. Experimental results showed that ESN can achieve comparable performance to bidirectional LSTM with shorter training time.…”

Section: Neural Networkmentioning

confidence: 99%

“…This paper proposes an IDS model based on reservoir computing (RC) to protect the IoV system. RC, as a framework for computation, has been successfully applied to address real-world problems in various domains, including time series forecasting, handwriting recognition, and network anomaly detection [16][17][18]. In contrast to typical recurrent neural networks (RNNs), RC offers computational efficiency with less memory demand, attributed to its architecture and training algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Lightweight Intrusion Detection Using Reservoir Computing

Deng,

Shen,

Feng

et al. 2024

CMC

View full text Add to dashboard Cite

The blockchain-empowered Internet of Vehicles (IoV) enables various services and achieves data security and privacy, significantly advancing modern vehicle systems. However, the increased frequency of data transmission and complex network connections among nodes also make them more susceptible to adversarial attacks. As a result, an efficient intrusion detection system (IDS) becomes crucial for securing the IoV environment. Existing IDSs based on convolutional neural networks (CNN) often suffer from high training time and storage requirements. In this paper, we propose a lightweight IDS solution to protect IoV against both intra-vehicle and external threats. Our approach achieves superior performance, as demonstrated by key metrics such as accuracy and precision. Specifically, our method achieves accuracy rates ranging from 99.08% to 100% on the Car-Hacking dataset, with a remarkably short training time.

show abstract

Section: Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%