Using a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) to Classify Network Attacks

Muhuri, Pramita Sree; Chatterjee, Prosenjit; Yuan, Xiaohong; Roy, Kaushik; Esterline, Albert

doi:10.3390/info11050243

Cited by 85 publications

(27 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…If the recorded information is no longer needed, forget gates can be used to reset the state of the linear unit. Simple sigmoid threshold units are used in these gates [30].…”

Section: Long Short Term Memory Methodsmentioning

confidence: 99%

A Novel Relaying Scheme Using Long Short Term Memory for Bipolar High Voltage Direct Current Transmission Lines

et al. 2021

View full text Add to dashboard Cite

In this paper, a novel protection scheme is proposed for bipolar line commutated converter (LCC) high voltage direct current (HVDC) transmission lines which detects the fault, identifies the pole of fault and estimates the location of fault. The scheme uses features extracted from rectifier end DC current and voltage signals. Long short term memory (LSTM) deep learning method has been designed as classifier as well as predictor for carrying out different protection tasks. Three modules have been designed namely LSTM-FD for fault detection, LSTM-FI for fault pole identification and LSTM-FL for fault location estimation. The extracted features are given as inputs to the specific protection module to carry out the tasks. All the protection modules have been tested varying fault type, location, resistance, smoothing reactors, noisy signals, etc. Sensitivity and reliability of the proposed protection scheme is 100% with all the tested fault cases. Error in location estimation is within 1% for all the tested fault cases. Advantage of the method is that it does not require communication link. Another advantage of the proposed method is that it can work with low sampling frequency. Yet another advantage of proposed method is that its reliability and sensitivity is very high, hence can be used as an alternative to travelling wave based protection schemes.

show abstract

“…If the recorded information is no longer needed, forget gates can be used to reset the state of the linear unit. Simple sigmoid threshold units are used in these gates [30].…”

Section: Long Short Term Memory Methodsmentioning

confidence: 99%

A Novel Relaying Scheme Using Long Short Term Memory for Bipolar High Voltage Direct Current Transmission Lines

et al. 2021

View full text Add to dashboard Cite

show abstract

“…This heterogeneous ensemble learning ensured that the model has better adaptability and accuracy when compared with other methods. The study by Muhuri et al [160] shows that the performance of the LSTM-RNN model is better in binary classification as compared to multiclass classification. In binary classification, the proposed model outperforms SVM and RF models.…”

Section: Review Of Various Deep Learning Techniques In Idsmentioning

confidence: 99%

Internet of Things Applications, Security Challenges, Attacks, Intrusion Detection, and Future Visions: A Systematic Review

2021

View full text Add to dashboard Cite

Internet of Things (IoT) technology is prospering and entering every part of our lives, be it education, home, vehicles, or healthcare. With the increase in the number of connected devices, several challenges are also coming up with IoT technology: heterogeneity, scalability, quality of service, security requirements, and many more. Security management takes a back seat in IoT because of cost, size, and power. It poses a significant risk as lack of security makes users skeptical towards using IoT devices. This, in turn, makes IoT vulnerable to security attacks, ultimately causing enormous financial and reputational losses. It makes up for an urgent need to assess present security risks and discuss the upcoming challenges to be ready to face the same. The undertaken study is a multi-fold survey of different security issues present in IoT layers: perception layer, network layer, support layer, application layer, with further focus on Distributed Denial of Service (DDoS) attacks. DDoS attacks are significant threats for the cyber world because of their potential to bring down the victims. Different types of DDoS attacks, DDoS attacks in IoT devices, impacts of DDoS attacks, and solutions for mitigation are discussed in detail. The presented review work compares Intrusion Detection and Prevention models for mitigating DDoS attacks and focuses on Intrusion Detection models. Furthermore, the classification of Intrusion Detection Systems, different anomaly detection techniques, different Intrusion Detection System models based on datasets, various machine learning and deep learning techniques for data pre-processing and malware detection has been discussed. In the end, a broader perspective has been envisioned while discussing research challenges, its proposed solutions, and future visions.

show abstract

“…The machine learning models for forecasting consists of a wide range of techniques-from the conventional forecasting methodologies such as ARIMA [18,19] and Exponential smoothing to newer deep learning approaches such as LSTM [20]. It is no surprise that it can become very challenging to apply several regression techniques over time-series data-as the time-series data tend to have sparse values, so they shelter larger contributions to randomness than the seasonality of the data.…”

Section: Executionmentioning

confidence: 99%

Rainfall Forecasting Using Machine Learning Algorithms for Localized Events

Ganapathy¹,

Srinivasan²,

Datta³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

A substantial amount of the Indian economy depends solely on agriculture. Rainfall, on the other hand, plays a significant role in agriculturewhile an adequate amount of rainfall can be considered as a blessing, if the amount is inordinate or scant, it can ruin the entire hard work of the farmers. In this work, the rainfall dataset of the Vellore region, of Tamil Nadu, India, in the years 2021 and 2022 is forecasted using several machine learning algorithms. Feature engineering has been performed in this work in order to generate new features that remove all sorts of autocorrelation present in the data. On removal of autocorrelation, the data could be used for performing operations on the time-series data, which otherwise could only be performed on any other regular regression data. The work uses forecasting techniques like the AutoRegessive Integrated Moving Average (ARIMA) and exponential smoothening, and then the time-series data is further worked on using Long Short Term Memory (LSTM). Later, regression techniques are used by manipulating the dataset. The work is benchmarked with several evaluation metrics on a test dataset, where XGBoost Regression technique outperformed the test. The uniqueness of this work is that it forecasts the daily rainfall for the year 2021 and 2022 in Vellore region. This work can be extended in the future to predict rainfall over a bigger region based on previously recorded time-series data, which can help the farmers and common people to plan accordingly and take precautionary measures.

show abstract

Using a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) to Classify Network Attacks

Cited by 85 publications

References 21 publications

A Novel Relaying Scheme Using Long Short Term Memory for Bipolar High Voltage Direct Current Transmission Lines

A Novel Relaying Scheme Using Long Short Term Memory for Bipolar High Voltage Direct Current Transmission Lines

Internet of Things Applications, Security Challenges, Attacks, Intrusion Detection, and Future Visions: A Systematic Review

Rainfall Forecasting Using Machine Learning Algorithms for Localized Events

Contact Info

Product

Resources

About