scholarly journals BCEAD: A Blockchain-Empowered Ensemble Anomaly Detection for Wireless Sensor Network via Isolation Forest

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Xiong Yang ◽  
Yuling Chen ◽  
Xiaobin Qian ◽  
Tao Li ◽  
Xiao Lv
Keyword(s):  
Anomaly Detection ◽  
Block Structure ◽  
Detection Algorithm ◽  
Wireless Sensor ◽  
Detection Systems ◽  
Blockchain Technology ◽  
The Internet Of Things ◽  
Isolation Forest ◽  
Distributed Deployment ◽  
Internal Attacks

The distributed deployment of wireless sensor networks (WSNs) makes the network more convenient, but it also causes more hidden security hazards that are difficult to be solved. For example, the unprotected deployment of sensors makes distributed anomaly detection systems for WSNs more vulnerable to internal attacks, and the limited computing resources of WSNs hinder the construction of a trusted environment. In recent years, the widely observed blockchain technology has shown the potential to strengthen the security of the Internet of Things. Therefore, we propose a blockchain-based ensemble anomaly detection (BCEAD), which stores the model of a typical anomaly detection algorithm (isolated forest) in the blockchain for distributed anomaly detection in WSNs. By constructing a suitable block structure and consensus mechanism, the global model for detection can iteratively update to enhance detection performance. Moreover, the blockchain guarantees the trust environment of the network, making the detection algorithm resistant to internal attacks. Finally, compared with similar schemes, in terms of performance, cost, etc., the results prove that BCEAD performs better.

scholarly journals Data Transmission Reduction in Wireless Sensor Network for Spatial Event Detection

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7256
Author(s):  
Marcin Lewandowski ◽  
Bartłomiej Płaczek
Keyword(s):  
Wireless Sensor Network ◽  
Sensor Network ◽  
Event Detection ◽  
Detection Algorithm ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Essential Requirement ◽  
Detection Systems ◽  
Transmission Reduction ◽  
Long Lifetime

Wireless sensor networks have found many applications in detecting events such as security threats, natural hazards, or technical malfunctions. An essential requirement for event detection systems is the long lifetime of battery-powered sensor nodes. This paper introduces a new method for prolonging the wireless sensor network’s lifetime by reducing data transmissions between neighboring sensor nodes that cooperate in event detection. The proposed method allows sensor nodes to decide whether they need to exchange sensor readings for correctly detecting events. The sensor node takes into account the detection algorithm and verifies whether its current sensor readings can impact the event detection performed by another node. The data are transmitted only when they are found to be necessary for event detection. The proposed method was implemented in a wireless sensor network to detect the instability of cargo boxes during transportation. Experimental evaluation confirmed that the proposed method significantly extends the network lifetime and ensures the accurate detection of events. It was also shown that the introduced method is more effective in reducing data transmissions than the state-of-the-art event-triggered transmission and dual prediction algorithms.

scholarly journals Extending Isolation Forest for Anomaly Detection in Big Data via K-Means

2021 ◽  
Vol 5 (4) ◽  
pp. 1-26
Author(s):  
Md Tahmid Rahman Laskar ◽  
Jimmy Xiangji Huang ◽  
Vladan Smetana ◽  
Chris Stewart ◽  
Kees Pouw ◽  
...  
Keyword(s):  
Big Data ◽  
Intrusion Detection ◽  
Anomaly Detection ◽  
Computer Networks ◽  
Network Traffic ◽  
Intrusion Detection Systems ◽  
Traffic Data ◽  
Detection Systems ◽  
Proposed Model ◽  
Isolation Forest

Industrial Information Technology infrastructures are often vulnerable to cyberattacks. To ensure security to the computer systems in an industrial environment, it is required to build effective intrusion detection systems to monitor the cyber-physical systems (e.g., computer networks) in the industry for malicious activities. This article aims to build such intrusion detection systems to protect the computer networks from cyberattacks. More specifically, we propose a novel unsupervised machine learning approach that combines the K-Means algorithm with the Isolation Forest for anomaly detection in industrial big data scenarios. Since our objective is to build the intrusion detection system for the big data scenario in the industrial domain, we utilize the Apache Spark framework to implement our proposed model that was trained in large network traffic data (about 123 million instances of network traffic) stored in Elasticsearch. Moreover, we evaluate our proposed model on the live streaming data and find that our proposed system can be used for real-time anomaly detection in the industrial setup. In addition, we address different challenges that we face while training our model on large datasets and explicitly describe how these issues were resolved. Based on our empirical evaluation in different use cases for anomaly detection in real-world network traffic data, we observe that our proposed system is effective to detect anomalies in big data scenarios. Finally, we evaluate our proposed model on several academic datasets to compare with other models and find that it provides comparable performance with other state-of-the-art approaches.

Sign in / Sign up

Export Citation Format

Share Document