Boosting-Based DDoS Detection in Internet of Things Systems

Cvitić, Ivan; Peraković, Dragan; Gupta, Brij B.; Choo, Kim‐Kwang Raymond

doi:10.1109/jiot.2021.3090909

Cited by 110 publications

(54 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This indicates that the Random Forest can still accurately recognise anomalized threatening behaviour that is unknown to the network administrator. The overall Accuracy of the Random Forest model is 99%, which is similar to the results obtained by [56][57][58][59][60]. The most important features are depicted in Figure 31 that presents the Mean Decrease value that measures the importance of a variable to estimate the target variable values of all the trees used by the Random Forest model [54].…”

Section: Results Of the Ensemble Learning Algorithmssupporting

confidence: 71%

“…It is a cryptovirus that encrypts multivariate user data with different formats, namely archive, video, audio, multimedia documents and much more. Lastly, we have compared the experimental results obtained by [56][57][58][59][60] to ours because of the Ensemble Learning approach that has been utilised on the fly of malware recognition. The Accuracy of the Ensemble Learning models utilised in [56][57][58][59][60] is illustrated in Table 13 where the performance achieved by selected algorithms is similar to the one obtained in this article.…”

Section: A Deeper Comparison Of the Ugransome Datasetmentioning

confidence: 99%

“…Lastly, we have compared the experimental results obtained by [56][57][58][59][60] to ours because of the Ensemble Learning approach that has been utilised on the fly of malware recognition. The Accuracy of the Ensemble Learning models utilised in [56][57][58][59][60] is illustrated in Table 13 where the performance achieved by selected algorithms is similar to the one obtained in this article. We can then argue that implementing the Ensemble Learning algorithms applied to the UGRansome dataset can facilitate accurate results to improve zero-day threats recognition for NIDSs.…”

Section: A Deeper Comparison Of the Ugransome Datasetmentioning

confidence: 99%

“…Algorithms Accuracy Dataset [56] RandomTree & DecisionStump 99% NSL-KDD [57] Network traffic anomalies detection 99% Legacy datasets [58] AI4SAFE-IoT 100% IOT [59] Boosting method of logistic model trees 99% DDoS traffic [60] Logistic Regression 99% IOT & Netflow…”

Section: Researchmentioning

confidence: 99%

“…The normal category consists of 91,360 patterns, whereas the abnormal stands at 56,598. The remaining category (59,576) represents the total of cyclostationary feature patterns in the UGRansome. These patterns are recorded in the normal and abnormal categories.…”

mentioning

confidence: 99%

See 4 more Smart Citations

UGRansome1819: A Novel Dataset for Anomaly Detection and Zero-Day Threats

2021

View full text Add to dashboard Cite

This research attempts to introduce the production methodology of an anomaly detection dataset using ten desirable requirements. Subsequently, the article presents the produced dataset named UGRansome, created with up-to-date and modern network traffic (netflow), which represents cyclostationary patterns of normal and abnormal classes of threatening behaviours. It was discovered that the timestamp of various network attacks is inferior to one minute and this feature pattern was used to record the time taken by the threat to infiltrate a network node. The main asset of the proposed dataset is its implication in the detection of zero-day attacks and anomalies that have not been explored before and cannot be recognised by known threats signatures. For instance, the UDP Scan attack has been found to utilise the lowest netflow in the corpus, while the Razy utilises the highest one. In turn, the EDA2 and Globe malware are the most abnormal zero-day threats in the proposed dataset. These feature patterns are included in the corpus, but derived from two well-known datasets, namely, UGR’16 and ransomware that include real-life instances. The former incorporates cyclostationary patterns while the latter includes ransomware features. The UGRansome dataset was tested with cross-validation and compared to the KDD99 and NSL-KDD datasets to assess the performance of Ensemble Learning algorithms. False alarms have been minimized with a null empirical error during the experiment, which demonstrates that implementing the Random Forest algorithm applied to UGRansome can facilitate accurate results to enhance zero-day threats detection. Additionally, most zero-day threats such as Razy, Globe, EDA2, and TowerWeb are recognised as advanced persistent threats that are cyclostationary in nature and it is predicted that they will be using spamming and phishing for intrusion. Lastly, achieving the UGRansome balance was found to be NP-Hard due to real life-threatening classes that do not have a uniform distribution in terms of several instances.

show abstract

Section: Results Of the Ensemble Learning Algorithmssupporting

confidence: 71%

Section: A Deeper Comparison Of the Ugransome Datasetmentioning

confidence: 99%

Section: A Deeper Comparison Of the Ugransome Datasetmentioning

confidence: 99%

Section: Researchmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

UGRansome1819: A Novel Dataset for Anomaly Detection and Zero-Day Threats

2021

View full text Add to dashboard Cite

show abstract

DDoS attack detection in cloud using ensemble model tuned with optimal hyperparameter

Reddy,

Meera

2024

Adaptive Control & Signal

View full text Add to dashboard Cite

SummaryDDoS attacks are a type of cloud incursion that lessen service degradation. DDoS attacks target the cloud network with invalid requests, rejecting legitimate requests. Such attacks disrupt the entire cloud architecture, thus it needs efficient detection methods to spot their presence. This study proposes a novel ensemble classification model for DDoS incursion detection. Pre‐processing, feature extraction, and attack detection are the three main components of the suggested intrusion detection system. Improved data imbalance processing is processed during pre‐processing. Features including HOS‐based features enhanced entropy‐based features, correlation features, and raw features are extracted from the pre‐processed data. The generated features are trained using an ensemble model, which integrates classifiers like SVM, RF, NN, LSTM, and DRN, during the attack detection phase. A new hybrid approach known as TUDMA optimally trains the model by setting the ideal weight because DRN provides the final detected outcome. By reducing errors, this ideal training will guarantee an improvement in detection results. The suggested hybrid optimization combines the two techniques, TDO and DMO. The accuracy of the methods FS‐WOA‐DNN, RBF‐PSO, SMA, BRO, SLO, and NMRA was 86.73%, 85.69%, 84.58%, 87.43%, 88.91%, and 89.78%, respectively, while the accuracy of the TUDMA was 95.34% in the 80th learning percentage. Finally, for many measurements, the suggested efficiency is superior to the traditional methods.

show abstract

Optimization of node deployment in underwater internet of things using novel adaptive long short‐term memory‐based egret swarm optimization algorithm

Simon,

Kapileswar,

Padmavathi

et al. 2024

Int J Communication

View full text Add to dashboard Cite

SummaryOptimizing node deployment in the underwater Internet of Things (UIoT) poses significant challenges due to the complex and dynamic nature of underwater environments. This research introduces the adaptive long short‐term memory‐based egret swarm optimization algorithm (ALSTM‐ESOA), a novel approach designed to enhance network coverage and performance efficiently. Unlike traditional methods, ALSTM‐ESOA incorporates cognitive learning capabilities from long short‐term memory (LSTM) and dynamic adaptation strategies inspired by the hunting behaviors of egrets. The algorithm's effectiveness was tested through extensive simulations in MATLAB, demonstrating notable improvements over existing models: network throughput increased by up to 55.56%, deployment time decreased by 88.89%, and energy efficiency improved significantly. These enhancements are critical for robust, real‐time data collection and monitoring in underwater settings, providing substantial benefits for marine research and resource management. The findings suggest that ALSTM‐ESOA significantly outperforms conventional algorithms, offering a promising new tool for the advancement of UIoT applications. After being implemented in MATLAB, the suggested ALSTM‐ESOA model for the node deployment optimization in UIoT is examined. The proposed ALSTM‐ESOA in terms of network throughput is 55.56%, 38.89%, 36.11%, and 11.11% better than CNN, LSTM, ARO‐RTP, and IGOR‐TSA, respectively. Similarly, the proposed ALSTM‐ESOA with respect to deployment time is 88.89%, 81.82%, 75%, and 50% better than CNN, LSTM, ARO‐RTP, and IGOR‐TSA, respectively. For the purpose of exploring marine resources, monitoring underwater environments, and conducting marine scientific investigation, the research's findings are extremely valuable.

show abstract

Boosting-Based DDoS Detection in Internet of Things Systems

Cited by 110 publications

References 37 publications

UGRansome1819: A Novel Dataset for Anomaly Detection and Zero-Day Threats

UGRansome1819: A Novel Dataset for Anomaly Detection and Zero-Day Threats

DDoS attack detection in cloud using ensemble model tuned with optimal hyperparameter

Optimization of node deployment in underwater internet of things using novel adaptive long short‐term memory‐based egret swarm optimization algorithm

Contact Info

Product

Resources

About