Wireless Sensor Network Intrusion Research Articles

MLSTL-WSN: machine learning-based intrusion detection using SMOTETomek in WSNs

In the domain of cyber-physical systems, wireless sensor networks (WSNs) play a pivotal role as infrastructures, encompassing both stationary and mobile sensors. These sensors self-organize and establish multi-hop connections for communication, collectively sensing, gathering, processing, and transmitting data about their surroundings. Despite their significance, WSNs face rapid and detrimental attacks that can disrupt functionality. Existing intrusion detection methods for WSNs encounter challenges such as low detection rates, computational overhead, and false alarms. These issues stem from sensor node resource constraints, data redundancy, and high correlation within the network. To address these challenges, we propose an innovative intrusion detection approach that integrates machine learning (ML) techniques with the Synthetic Minority Oversampling Technique Tomek Link (SMOTE-TomekLink) algorithm. This blend synthesizes minority instances and eliminates Tomek links, resulting in a balanced dataset that significantly enhances detection accuracy in WSNs. Additionally, we incorporate feature scaling through standardization to render input features consistent and scalable, facilitating more precise training and detection. To counteract imbalanced WSN datasets, we employ the SMOTE-Tomek resampling technique, mitigating overfitting and underfitting issues. Our comprehensive evaluation, using the wireless sensor network dataset (WSN-DS) containing 374,661 records, identifies the optimal model for intrusion detection in WSNs. The standout outcome of our research is the remarkable performance of our model. In binary classification scenarios, it achieves an accuracy rate of 99.78%, and in multiclass classification scenarios, it attains an exceptional accuracy rate of 99.92%. These findings underscore the efficiency and superiority of our proposal in the context of WSN intrusion detection, showcasing its effectiveness in detecting and mitigating intrusions in WSNs.

A trusted effective approach for forecasting the failure of data link and intrusion in wireless sensor networks

Wireless sensor network (WSN) is often utilised in many different industries for a variety of purposes. The improved network access area and quick network setup make it an excellent technology. However, certain eradicating problems will also be present, slowing the expansion of the network. The forecasting of connection failure is still thought to be a mystery in the WSN area. The suggested method provides a thorough understanding of connection failure. This method introduces the proficient trustworthy Node ID dependent resource reservation protocol (PTN-RRP). Then, using technique weighted on end-to-end latency, the shortest path is identified. Major issues with WSN include data link failure and intrusions. This method might increase the rate of detection since it determines the shortest route from a particular preliminary point to the target. The hop address and sequence number are added to the protocol by determining the shortest path. Following the discovery of the shortest path, the likelihood of connection failure is calculated. The established trustworthy etiquette adopted has a link failure structure that can foresee and resolve connection failure-related problems. After that, a posterior probability evaluation approach is used to determine the type of assault in order to determine the attack reason intended for the connection failure. Finally, a simulation study is used to evaluate the performance of the suggested strategy. The simulation's results show that the proposed technique is extremely successful in identifying link breaks, and the developed algorithm for recognising the shortest path will shorten the time required to find the shortest way. To demonstrate the usefulness of the suggested methodology, the performance result is contrasted with currently used procedures.

Optimization assisted deep learning based intrusion detection system in wireless sensor network with two‐tier trust evaluation

AbstractNowadays, owing to the openness of transmission medium, wireless sensor networks (WSNs) suffer from a variety of attacks, together with DoS attacks, tampering attacks, sinkhole attacks, and so on. Therefore, an effectual system is necessary for recognizing the intrusions in WSN. This paper aims to set up a novel intrusion detection system (IDS) via a deep learning model. Initially, optimal cluster head (CH) is selected among the sensor nodes, from which the sensor nodes that have high energy will be prioritized to act as CH. In this proposed work, the CH selection is evaluated optimally by not only considering the energy parameter, further under the constraints like delay and distance. For optimal selection, a novel approach named as self‐improved sea lion optimization (SI‐SLnO) model is introduced in this work. As per the proposed strategy, the trust of CH and nodes is evaluated based on a multidimensional two‐tier hierarchical trust model by considering content trust, honesty trust, and interactive trust. Finally, the deep learning‐based intrusion detection takes place via optimized neural network (NN), where the training is done by the proposed SI‐SLnO algorithm via the optimal weight tuning process. At last, the supremacy of the developed approach is examined via evaluation over numerous extant techniques.

Artificial Flora Optimization Algorithm with Functional Link Neural Network for DoS Attack Classification in WSN

Wireless sensor networks (WSN) is widely utilized for collecting data related to physical parameters from the environment. Security remains a challenging issue in the design of WSN. Security in WSN from Denial of Service (DoS) attack is an important security risk. This study introduces an artificial flora optimization algorithm with functional link neural network (AFOA-FLNN) model for DoS attack classification in WSN. The presented AFOA-FLNN model initially undergoes data pre-processing to transform the data into meaningful way. Secondly, the FLNN model is utilized for the effective recognition and classification of intrusions in WSN. Finally, the AFOA is exploited for optimally tuning the parameters involved in the FLNN model and results in enhanced performance. In order to demonstrate the better outcomes of the AFOA-FLNN model, a wide-ranging experimentation assessment on test data and the results pointed out the improved outcomes of the AFOA-FLNN model.

Improved binary gray wolf optimizer and SVM for intrusion detection system in wireless sensor networks

Intrusion in wireless sensor networks (WSNs) aims to degrade or even eliminating the capability of these networks to provide its functions. In this paper, an enhanced intrusion detection system (IDS) is proposed by using the modified binary grey wolf optimizer with support vector machine (GWOSVM-IDS). The GWOSVM-IDS used 3 wolves, 5 wolves and 7 wolves to find the best number of wolves. The proposed method aims to increase intrusion detection accuracy and detection rate and reduce processing time in the WSN environment through decrease false alarms rates, and the number of features resulted from the IDSs in the WSN environment. Indeed, the NSL KDD’99 dataset is used to demonstrate the performance of the proposed method and compare it with other existing methods. The proposed methods are evaluated in terms of accuracy, the number of features, execution time, false alarm rate, and detection rate. The results showed that the proposed GWOSVM-IDS with seven wolves overwhelms the other proposed and comparative algorithms.

Interference and Intrusion in Wireless Sensor Networks

Wireless sensor network (WSN) systems for safety-critical, space and Internet of Things applications have recently begun to adopt open standards and commercial-off-the-shelf equipment, and persistently face challenges of malicious intrusion and spectrum coexistence. These threats are explored through Monte-Carlo simulation and benchtop testing, including matched protocol interference and sophisticated, interactive intrusion attacks. The need for expanding intrusion detection via a more holistic approach, whilst simultaneously improving WSN security, is illustrated. Discussions on WSN security, vulnerabilities, and attacks are also provided.

Identity verification-based cryptography for detecting intrusion in wireless sensor networks

Identity verification-based cryptography for detecting intrusion in wireless sensor networks

Identity verification-based cryptography for detecting intrusion in wireless sensor networks

Identity Verification Based Cryptosystem (IDVBC) mechanism is implemented here for providing a novel and secure data transmission among nodes. Here, token-based node identity verification along with certificates and data encoding mechanism is carried out to reduce the complexity in wireless networks. By applying local identity verification scheme, the communication overheads get reduced and hence the certificate management process is simplified. Each sensor owns a local private key and should get matched with the public key generated by the base station. Encoding process uses hash signature schemes for enhancing the security measures in the network. Source node sends the encrypted or encoded data with the generated local private key and labelled token ID. Once the token ID verification is done and the key matches with the global private key generated by the BS, the decrypted or decoded data is received by the receiver. The proposed IDVBC scheme has the ability to detect malicious activity of the node, to provide high-level security and able to tolerate several security attacks. Proposed scheme is improved with 39% efficiency better than the conventional method in terms of secured data transmission.

Achieving Crossed Strong Barrier Coverage in Wireless Sensor Network.

Barrier coverage has been widely used to detect intrusions in wireless sensor networks (WSNs). It can fulfill the monitoring task while extending the lifetime of the network. Though barrier coverage in WSNs has been intensively studied in recent years, previous research failed to consider the problem of intrusion in transversal directions. If an intruder knows the deployment configuration of sensor nodes, then there is a high probability that it may traverse the whole target region from particular directions, without being detected. In this paper, we introduce the concept of crossed barrier coverage that can overcome this defect. We prove that the problem of finding the maximum number of crossed barriers is NP-hard and integer linear programming (ILP) is used to formulate the optimization problem. The branch-and-bound algorithm is adopted to determine the maximum number of crossed barriers. In addition, we also propose a multi-round shortest path algorithm (MSPA) to solve the optimization problem, which works heuristically to guarantee efficiency while maintaining near-optimal solutions. Several conventional algorithms for finding the maximum number of disjoint strong barriers are also modified to solve the crossed barrier problem and for the purpose of comparison. Extensive simulation studies demonstrate the effectiveness of MSPA.

MP-MID: Multi-Protocol Oriented Middleware-level Intrusion Detection method for wireless sensor networks

It is very difficult to detect intrusions in wireless sensor networks (WSN), because of its dynamic network topology and diverse routing protocols. Traditional Intrusion Detection Systems (IDS) for WSN only focus attention on some one routing protocol, which lacks universality and flexibility. To solve the problem of multi-protocol intrusion detection, this paper proposes a universal method: MP-MID (Multi-Protocol Oriented Middleware-level Intrusion Detection). Our work can generate all known attack types for any routing protocol of WSN, and furthermore, all of them can be detected with the automatically generated rules. In this work, we formalize the routing protocol with the Process Algebra for Wireless Mesh Networks (AWN) language, and propose the conception of attack points to find out all attack types. Combining attack points with formalized protocol in AWN, we get co-sentences which represent the attack features in the protocol. With program slicing technology, all known attack types can be found out based on co-sentences. According to the characteristic of the key variables of the attack types, MP-MID can generate misused based detection or anomaly based detection. Our case study of ADOV (Ad hoc On-demand Distance Vector) protocol shows that our method generated all types of attacks, which outperforms other work. Experimental results show that our generated detection methods have a relatively high detection accuracy rate as we claimed. Our MP-MID method could be used as a flexible and universal tool to analyze and detect attack types for multi-protocol in WSN effectively.

Co-FAIS: Cooperative fuzzy artificial immune system for detecting intrusion in wireless sensor networks

Due to the distributed nature of Denial-of-Service attacks, it is tremendously challenging to identify such malicious behavior using traditional intrusion detection systems in Wireless Sensor Networks (WSNs). In the current paper, a bio-inspired method is introduced, namely the cooperative-based fuzzy artificial immune system (Co-FAIS). It is a modular-based defense strategy derived from the danger theory of the human immune system. The agents synchronize and work with one another to calculate the abnormality of sensor behavior in terms of context antigen value (CAV) or attackers and update the fuzzy activation threshold for security response. In such a multi-node circumstance, the sniffer module adapts to the sink node to audit data by analyzing the packet components and sending the log file to the next layer. The fuzzy misuse detector module (FMDM) integrates with a danger detector module to identify the sources of danger signals. The infected sources are transmitted to the fuzzy Q-learning vaccination modules (FQVM) in order for particular, required action to enhance system abilities. The Cooperative Decision Making Modules (Co-DMM) incorporates danger detector module with the fuzzy Q-learning vaccination module to produce optimum defense strategies. To evaluate the performance of the proposed model, the Low Energy Adaptive Clustering Hierarchy (LEACH) was simulated using a network simulator. The model was subsequently compared against other existing soft computing methods, such as fuzzy logic controller (FLC), artificial immune system (AIS), and fuzzy Q-learning (FQL), in terms of detection accuracy, counter-defense, network lifetime and energy consumption, to demonstrate its efficiency and viability. The proposed method improves detection accuracy and successful defense rate performance against attacks compared to conventional empirical methods.

Cooperative game theoretic approach using fuzzy Q-learning for detecting and preventing intrusions in wireless sensor networks

Owing to the distributed nature of denial-of-service attacks, it is tremendously challenging to detect such malicious behavior using traditional intrusion detection systems in Wireless Sensor Networks (WSNs). In the current paper, a game theoretic method is introduced, namely cooperative Game-based Fuzzy Q-learning (G-FQL). G-FQL adopts a combination of both the game theoretic approach and the fuzzy Q-learning algorithm in WSNs. It is a three-player strategy game consisting of sink nodes, a base station, and an attacker. The game performs at any time a victim node in the network receives a flooding packet as a DDoS attack beyond a specific alarm event threshold in WSN. The proposed model implements cooperative defense counter-attack scenarios for the sink node and the base station to operate as rational decision-maker players through a game theory strategy. In order to evaluate the performance of the proposed model, the Low Energy Adaptive Clustering Hierarchy (LEACH) was simulated using NS-2 simulator. The model is subsequently compared against other existing soft computing methods, such as fuzzy logic controller, Q-learning, and fuzzy Q-learning, in terms of detection accuracy, counter-defense, network lifetime and energy consumption, to demonstrate its efficiency and viability. The proposed model׳s attack detection and defense accuracy yield a greater improvement than existing above-mentioned machine learning methods. In contrast to the Markovian game theoretic, the proposed model operates better in terms of successful defense rate.

A Delay-Tolerant Virtual Tunnel Scheme for Asynchronous MAC protocols in WSN

Typically, asynchronous MAC protocols are used to monitor a significant facility for rare events or to detect an intrusion in wireless sensor networks. Moreover, asynchronous MAC protocols can achieve high energy efficiency due to the fact that there is no periodic control frame. However, asynchronous MAC protocols have the problem of long end-to-end delay time caused by the absence of precedent time synchronization per link. This paper proposes a new scheme, called virtual tunnel (VT), which can reduce the delivery delay of asynchronous MAC protocols in multi-hop environment. The VT scheme can achieve approximated duty cycle synchronization with on-demand approach. In this scheme, through the estimation of next wakeup time of peer node, without exceptional process, each node on the transmission path can improve end-to-end delay in multi-hop topologies. And it becomes low power consumption by reducing unnecessary retransmissions. Additionally, we devise the protection method of VT. In our simulation results, end-to-end delay according to hop counts and traffic amount is compared with the X-MAC that is an asynchronous protocol recently developed. Furthermore, it is shown that the VT scheme decreases energy consumption due to the lower end-to-end delay than the X-MAC in multi-hop topologies.

A survey of Intrusion Detection Systems for Wireless Sensor Networks

Wireless Sensor Networks (WSNs) are vulnerable to various kinds of security threats that can degrade the performance of the network and may cause the sensors to send wrong information to the sink. Key management, authentication and secure routing protocols cannot guarantee the required security for WSNs. Intrusion Detection System (IDS) provides a solution to this problem by analysing the network in order to detect abnormal behaviour of the sensor node(s). Researchers have proposed various approaches for detecting intrusions in WSNs during the past few years. In this survey, we classify these approaches into three categories and discuss them in detail.

A Rule Based Approach for Attribute Selection and Intrusion Detection in Wireless Sensor Networks

In this paper, we propose a new rule based attribute selection algorithm for removing the redundant attributes which are used in decision making on intrusions in wireless sensor networks. This work focuses mainly on finding important attributes to find Denial of Service attacks. In addition, we used an enhanced MSVM classification algorithm that was developed by extending the existing MSVM algorithm. Theexperimentalresultsshowthatthe proposed methods provide high detection rates and reduce false alarm rate. This system has been tested using KDD’99 Cup data set.

Anomaly intrusion detection in wireless sensor networks

We propose lightweight methods to detect anomaly intrusions in wireless sensor networks (WSNs). The main idea is to reuse the already available system information that is generated at various layer...