Performance Evaluation of Machine Learning Techniques for DOS Detection in Wireless Sensor Network

Alsulaiman, Lama; Al-Ahmadi, Saad

doi:10.5121/ijnsa.2021.13202

Cited by 28 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lama Alsulaiman et al (2021) suggested work conducts an experiment utilizing the Waikato Environment for Knowledge Analysis (WEKA) for assessing the efficacy of five machine learning (ML) techniques for identifying floods, grey holes, black holes, and scheduling DoS attacks on wireless sensor networks. The evaluation depends on the WSN-DS data collection.…”

Section: Literature Surveymentioning

confidence: 99%

See 1 more Smart Citation

Effective detection of DoS attack in wireless sensor network using ASFO algorithm and Improved Deep Convolutional Neural Network

2023

Preprint

View full text Add to dashboard Cite

Wireless sensor networks (WSN) are rapidly growing in popularity, and their flexibility and ease of implementation cause an increasing number of security issues, making it critical to research network intrusion defense for wireless sensor networks. Denial of service (DoS) is a cyber-attack that shuts down the targeted network. A DoS attack on a WSN device will be fatal. It is prone to malicious attacks and difficult to prevent because every single node is independent of the others, yet there's no central or monitoring node, which is tough to avoid. Numerous lightweight authentication systems have been utilized in real-time to ensure encrypted communication. However, with the lack of synchronization between nodes during data routing, WSNs are highly prone to Denial of Service (DoS) attacks. This article combines the Adaptive Sunflower Optimization (ASFO) method with an improved Deep Convolutional Neural Network (IDCNN) to enhance the degree of security against DoS attacks on WSNs term ASFO-IDCNN. This paper initially utilizes the ASFO method to improve the initial values of IDCNN to prevent getting into the local optimum. Then, the ASFO-IDCNN technique is used to detect intrusions in WSNs. The results of numerous simulated situations are shown, and the associated data is compared. DoS protection research is precious in analyzing the anti-attack efficiency of WSN nodes. The influence of DoS attacks on the functioning of WSNs is considered in this research.

show abstract

Section: Literature Surveymentioning

confidence: 99%

“…The evaluation depends on the WSN-DS data collection. The Random Forest (RF) classifier surpasses conventional methods with 99.72% accuracy [16].…”

Section: Literature Surveymentioning

confidence: 99%

Effective detection of DoS attack in wireless sensor network using ASFO algorithm and Improved Deep Convolutional Neural Network

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Furthermore, spoofing, rotation, and replay attacks jeopardize the integrity of the data. The network is designed on a custom architecture with WSN characteristics, which is the cause of these various attacks [24]. Derives from the network's ad-hoc structure, which includes WSN features.…”

Section: Attacks On the Network Layermentioning

confidence: 99%

Applying TTIED-CMYK Algorithm in Wireless Sensor Networks Based on Raspberry pi and DHT-11

Noor Sattar Noor,

Dalal Abdulmohsin Hammood,

Ali Al-Naji

2022

View full text Add to dashboard Cite

Recently, there has been a wide and continuous development in wireless sensor networks WSNs. These networks are directly employed in our daily lives, so it has become necessary to maintain the confidentiality of information in these networks. This paper provided a detailed explanation of the types of attackers according to their layer, in addition to the design of a wireless sensor network consisting of a temperature and humidity sensor called the DHT-11 and a Raspberry Pi to implement the Text-To-Image Encryption/Decryption algorithm based on CMYK mode (TTIED-CMYK) in these networks. An encrypted image with dimensions of 2×2 and a size not exceeding 70 bytes was obtained for a text consisting of eleven characters. In addition to that, the encryption time is very short, not exceeding 1 microsecond.

show abstract

“…The dataset for wireless sensor network intrusion detection is referred to as WSN_DS. The dataset represents a variety of denial of service (DoS) attacks, including blackhole, flooding, gray hole, and scheduling attacks, with 19 features and 374,661 records [5,6]. The KDD'99 dataset was created by simulating routine and traffic attacks in a military environment, specifically the US Air Force LAN [4].…”

Section: Introductionmentioning

confidence: 99%

Web Attack Intrusion Detection System Using Machine Learning Techniques

Baklizi,

Atoum,

Alkhazaleh

et al. 2024

Int. J. Onl. Eng.

View full text Add to dashboard Cite

Web attacks often target web applications because they can be accessed over a network and often have vulnerabilities. The success of an intrusion detection system (IDS) in detecting web attacks depends on an effective traffic classification system. Several previous studies have utilized machine learning classification methods to create an efficient IDS with various datasets for different types of attacks. This paper utilizes the Canadian Institute for Cyber Security’s (CIC-IDS2017) IDS dataset to assess web attacks. Importantly, the dataset contains 80 attributes of recent assaults, as reported in the 2016 McAfee report. Three machine learning algorithms have been evaluated in this research, namely random forests (RF), k-nearest neighbor (KNN), and naive bayes (NB). The primary goal of this research is to propose an effective machine learning algorithm for the IDS web attacks model. The evaluation compares the performance of three algorithms (RF, KNN, and NB) based on their accuracy and precision in detecting anomalous traffic. The results indicate that the RF outperformed the NB and KNN in terms of average accuracy achieved during the training phase. During the testing phase, the KNN algorithm outperformed others, achieving an average accuracy of 99.4916%. However, RF and KNN achieved 100% average precision and recall rates compared to other algorithms. Finally, the RF and KNN algorithms have been identified as the most effective for detecting IDS web attacks.

show abstract

Performance Evaluation of Machine Learning Techniques for DOS Detection in Wireless Sensor Network

Cited by 28 publications

References 13 publications

Effective detection of DoS attack in wireless sensor network using ASFO algorithm and Improved Deep Convolutional Neural Network

Effective detection of DoS attack in wireless sensor network using ASFO algorithm and Improved Deep Convolutional Neural Network

Applying TTIED-CMYK Algorithm in Wireless Sensor Networks Based on Raspberry pi and DHT-11

Web Attack Intrusion Detection System Using Machine Learning Techniques

Contact Info

Product

Resources

About