Implementation of intrusion detection model for DDoS attacks in Lightweight IoT Networks

Khanday, Shahbaz Ahmad; Fatima, Hoor; Rakesh, Nitin

doi:10.1016/j.eswa.2022.119330

Cited by 51 publications

(12 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To prove the effectiveness of our proposal in binary classification, we compared our results with two recent studies on IoT intrusion detection using the same dataset [24] and [30], focusing on two cases: Normal vs. All Attacks and Normal vs. DDoS Attacks. Table 5 shows the performance results of binary classification on the Bot-IoT dataset for the two specific cases.…”

Section: Resultsmentioning

confidence: 99%

An Adversarial Environment Reinforcement Learning-driven Intrusion Detection Algorithm for Internet of Things

Mahjoub,

Hamdi,

Alkanhel

et al. 2023

Preprint

View full text Add to dashboard Cite

The increasing prevalence of Internet of Things (IoT) systems has made them attractive targets for malicious actors. To address the evolving threats and the growing complexity of detection, there is a critical need to search for and develop new algorithms that are fast and robust in detecting and classifying dangerous network traffic. In this context, Deep Reinforcement Learning (DRL) is gaining recognition as a prospective solution in numerous fields as it enables autonomous agents to cooperate with their environment for decision-making without relying on human experts. This article presents a novel approach to intrusion detection in IoT systems through the utilization of an adversarial reinforcement learning (RL) algorithm, known for its exceptional predictive capabilities. The predictive process relies on a classifier, which is implemented as a streamlined and highly efficient neural network. Embedded within this classifier is a policy function, meticulously trained using an innovative RL model. Importantly, this model ensures that the environment’s behavior is dynamically fine-tuned simultaneously with the learning process, improving the overall effectiveness of the intrusion detection approach. The efficiency of our proposal was assessed using the Bot-IoT database, consisting of a mixture of legitimate IoT network traffic and simulated attack scenarios. Our scheme shows superior performance compared to existing ones. Therefore, our approach to IoT intrusion detection can be considered a valuable alternative to existing methods, capable of significantly improving the IoT systems’ security.

show abstract

Section: Resultsmentioning

confidence: 99%

An Adversarial Environment Reinforcement Learning-driven Intrusion Detection Algorithm for Internet of Things

Mahjoub,

Hamdi,

Alkanhel

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Where, k t is the t th cumulants, μ represented as mean, and 3 m is the third central moment. Where E represents the expectation operator, σ indicates the standard deviation, μ represents the mean, 3 m is the third central moment, and k t is the t th cumulants. The final equality indicates skewness regarding the correlation between the third cumulant k 3 and the second cumulant's k 2 1.5th power.…”

Section: Feature Extraction 321 Statistical Featuresmentioning

confidence: 99%

“…Security in IoT is one of the major issues these days due to various attacks in the real-time environment from hackers and virus programmers [2]. Early detection can limit these issues' significant effects on IoT networks [3]. The fast improvement of technological advancements leads to a chance where worms, viruses, and attacks threaten computers and networks [4].…”

Section: Introductionmentioning

confidence: 99%

Network intrusion classification for IoT networks using an extreme learning machine

Akuthota,

Bhargava

2024

Eng. Res. Express

View full text Add to dashboard Cite

The detection of intrusions has a significant impact on providing information security, and it is an essential technology to recognize diverse network threats effectively. This work proposes a machine learning technique to perform intrusion detection and classification using multiple feature extraction and testing using an Extreme learning machine (ELM). The model is evaluated on the two network intrusion datasets (NSL-KDD and UNSW-NB15), which consist of real-time network traffic. The arithmetic, gradient, and statistical features were extracted and evaluated with the proposed model. The method's efficacy is assessed using accuracy, sensitivity, specificity, precision, and F1-score. The proposed method achieves 94.5%, 97.61%, 96.91%, 96.51%, and 97.05% accuracy, sensitivity, specificity, precision, and F1-score for NSL-KDD and 94.3%, 98,36%, 99.31%, 99.67% and 99.01% of accuracy, sensitivity, specificity, precision and F1-score for the UNSWNB-15 dataset respectively, which is better performance outcomes when compared to other existing works.

show abstract

“…The former identifies attacks by manually maintaining a list of detection rules, which is commonly used in industrial security products. The latter [2][3][4][5][6][7][8][9][10][11] involves training a machine learning model for detection. The drawback of the former lies in the expensive manual maintenance of detection rules, while the latter requires security experts to perform feature engineering.…”

Section: Introductionmentioning

confidence: 99%

“…However, due to limitations in expert knowledge, the defined feature engineering approaches have their own flaws. For instance, the flow header features and Hrust features proposed in [2][3] cannot detect all types of DDoS attacks, and the methods presented in [4][5][6][7][8][9][10][11] can only detect DDoS attacks initiated by IoT botnets.…”

Section: Introductionmentioning

confidence: 99%

DDoS attack detection model based on CNN-LSTM

Min,

Yang,

Sun

et al. 2023

Fourth International Conference on Signal Processing and Computer Science (SPCS 2023)

View full text Add to dashboard Cite

Implementation of intrusion detection model for DDoS attacks in Lightweight IoT Networks

Cited by 51 publications

References 36 publications

An Adversarial Environment Reinforcement Learning-driven Intrusion Detection Algorithm for Internet of Things

An Adversarial Environment Reinforcement Learning-driven Intrusion Detection Algorithm for Internet of Things

Network intrusion classification for IoT networks using an extreme learning machine

DDoS attack detection model based on CNN-LSTM

Contact Info

Product

Resources

About