Misbehavior Detection Research Articles

Exploiting machine learning and deep learning models for misbehavior detection in VANET

There is an unprecedented proliferation of vehicular traffic data as the number of interconnected vehicles has increased in Vehicular Ad Hoc Networks (VANET) scenario to realize the goals of Intelligent Transportation Systems (ITS). As a result, the quantity and variety of attacks using transmitted data have risen. However, these broadcasted messages can be used to launch many security attacks as these messages are not encrypted. With the increase in the number of vehicles, the risk of misbehavior also increases as more malicious vehicles broadcast inaccurate and faulty messages. Various trust-based and deterministic misbehavior detection techniques have been proposed to identify such misbehavior. Existing solutions only address specific types of network intrusions. However, because VANET situations may involve a wide spectrum of attacks, a more robust misbehavior detection mechanism is required. This article compares the performance of several machine learning and deep learning architectures using key evaluation metrics. Furthermore, we have demonstrated a comparison of performance metrics with existing learning model-based techniques in different network scenarios.

To Tolerate or To Impute Missing Values in V2X Communications Data?

Misbehavior detection is a critical task in vehicular <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ad hoc</i> networks (VANETs). However, state-of-the-art data-driven techniques for misbehavior detection are usually conducted through complete V2X communications data collected from simulated experiments. This article evaluates main strategies for the treatment of missing values to find out the best match for misbehavior detection with incomplete V2X communications data. This article proposes two novel methods for imputing and tolerating missing data. The former is a novel imputation method that is based on the collaborative clustering and the latter is a missing-tolerant method that is an ensemble learning based on the random subspace selection and Dempster–Shafer fusion. The effectiveness of the proposed techniques is evaluated by the ground-truth vehicular reference misbehavior (VeReMi) data. Moreover, a multifactor amputation framework has been developed to induce missingness over V2X communications data with different missing ratios, mechanisms, and distributions. This provides a comprehensive benchmark resembling missingness over V2X communications data. The proposed methods are compared with five missing-tolerant and nine imputation methods. The attained results over the benchmark data indicate that the proposed missing-tolerant method is significantly better than other treatment methods in terms of accuracy and F-measure.

Comprehensive Review on Misbehavior Detection for Vehicular Ad Hoc Networks

Vehicular ad hoc networks (VANETs) can increase road safety and comfort. It needs strong demand for security because the data sent in VANETs influence vehicles’ behavior. Existing studies have summarized VANET security, challenge, and attacks. This study aims to present a comprehensive overview of misbehavior detection in VANETs. First, VANET characteristics, security issues, and attacks are discussed. Then, the precise definition of misbehavior, detection mode, and detection objects are presented. Generic misbehavior detection is classified as data-centric and node-centric. In this study, to adapt to the VANETs scenario, we proposed a novel taxonomy of misbehavior detection, which considers the interaction between vehicles and which is refined by emphasizing the detection modes and participants. Finally, the remaining concerns, open issues, and prospective future research directions are discussed.

Detecting and Preventing Misbehaving Intruders in the Internet of Vehicles

The advent of new vehicular advances and accessibility of new network access mediums have evolved service providers with heterogeneous-vehicular collaboration. The performance of heterogeneous-vehicular collaboration depends on the possibility of accurate, up-to-date vehicular information shared by Cooperative- Awareness Messages (CAMs) among neighboring vehicles. Although exchanging wrong mobility coordinates leading to disruption on the Internet of Vehicles (IoVs) applicability. To address these issues, a misbehavior detection approach is proposed which acts as a second wall of defense. Our scheme is divided into three phases context procurement, context sharing, and misbehavior detection. Mathematical modeling has been done to evaluate Sybil attack and false message generation attack detection under misbehavior detection. The proposed scheme attains 99% in detecting false message generation attacks and 98.5% in detecting Sybil attacks. Additionally, false-positive rate, overhead detection, and False-Measures are evaluated which demonstrates the effectiveness of our approach.

Fast and Progressive Misbehavior Detection in Internet of Vehicles Based on Broad Learning and Incremental Learning Systems

In recent years, deep learning (DL) has been widely used in vehicle misbehavior detection and has attracted great attention due to its powerful nonlinear mapping ability. However, because of the large number of network parameters, the training processes of these methods are time consuming. Besides, the existing detection methods lack scalability; thus, they are not suitable for Internet of Vehicles (IoV) where new data are constantly generated. In this article, the concept of the broad learning system (BLS) is innovatively introduced into vehicle misbehavior detection. In order to make better use of vehicle information, key features are first extracted from the collected raw data. Then, a BLS is established, which is able to calculate the connection weight of the network efficiently and effectively by ridge regression approximation. Finally, the system can be updated and refined by an incremental learning algorithm based on the newly generated data in IoV. The experimental results show that the proposed method performs much better than DL or traditional classifiers, and could update and optimize the old model fastly and progressively while improving the system’s misbehavior detection accuracy.

Physics-Based Misbehavior Detection System for V2X Communications

Physics-Based Misbehavior Detection System for V2X Communications

Lane Line Misbehaviour Detection using Hybrid Optimization - based Improved Convolution Neural Network

Lane Line Misbehaviour Detection using Hybrid Optimization - based Improved Convolution Neural Network

Improving routing disruption attack detection in MANETs using efficient trust establishment

AbstractSecurity is a fundamental prerequisite in self‐evolvability network and providing that in any situation is the most problematic task as the network is highly dynamic with no trusted centralized monitoring. On comparing with wired networks MANETs are highly susceptible to security attacks. This article proposed an efficient trust establishment‐based routing evidence scheme (ETERE) that carried out in the creation and manipulation of mental representations of information identified. Here, propose I‐Trust, probabilistic node misbehavior detection, for secure MANET routing toward ETERE scheme. The fundamental concept of I‐Trust is presenting a periodically accessible trusted authority to pass judgment on the behavior of a node dependent on the gathered routing evidences and with self and coordinate monitoring. The main advantage of ETERE scheme is that even if the hackers or the internal attackers have the knowledge of the security scheme, the system cannot be compromised. The performance of ETERE scheme with different routing disturbance attacks is evaluated in this article. The computational outcomes emphasize the effectiveness of ETERE scheme and ensure the routing efficiency. The NS2 simulator is used in this research work. The simulation results show that the proposed ETERE scheme performs better than present methodologies improving the PDR and throughput of the network to a maximum extent of 28% and 34% respectively.

TFMD-SDVN: a trust framework for misbehavior detection in the edge of software-defined vehicular network

TFMD-SDVN: a trust framework for misbehavior detection in the edge of software-defined vehicular network

An Improved Robust Misbehavior Detection Scheme for Vehicular Ad Hoc Network

Vehicular Ad Hoc Networks (VANETs) have emerged to improve road safety and traffic efficiency and provide passengers comfort. Most VANET applications rely on the cooperation among vehicles sharing their sensed information. However, misbehaving vehicles which send false information can disrupt the VANETs potential. Although many solutions have been proposed to defend against misbehaving vehicles in VANET, most of these solutions relays on honest majority assumptions and are thus vulnerable to collusion attacks. Colluding vehicles send fake information, and because detection depends on cooperation, such information misleads benign vehicles to make an accurate decision. This study proposes an improved Robust Misbehavior Detection Scheme (iRMDS) by replacing the statistics-based detection threshold, which assumes an honest majority, with a machine learning-based classifier. A Neuro-Kalman-Based Robust Misbehavior detection scheme is proposed in three phases. In the first phase, attackers-Independent features are extracted from signal properties such as the receive signal strength and signal direction and have been integrated with context information features. In the second phase, the Kalman filter algorithm has been designed to extract consistent patterns of context information for each vehicle. That is, the innovation errors of the Kalman filter have been utilized as the input features to train the misbehavior detection model. In the third phase, the artificial neural network algorithm is integrated with the outputs of the Kalman Filter algorithm to recognize the malicious pattern. Results show that the overall performance of the proposed iRMDS solution achieves a 3.44% improvement compared to the related work. Such enhancement is promising in realizing reliable VANET applications to improve road safety, traffic efficiency, and passenger comfort.

Machine Learning Based Misbehaviour Detection in VANET Using Consecutive BSM Approach

Vehicular ad-hoc network (VANET) is an emerging technology for vehicle-to-vehicle communication vital for reducing road accidents and traffic congestion in an Intelligent Transportation System (ITS). VANET communication is vulnerable to various attacks and cryptographic techniques are commonly used for message integrity and authentication of vehicles. However, cryptograhpic techniques alone may not be sufficient to protect against insider attacks. Many VANET safety applications rely on periodic broadcast of basic safety messages (BSMs) from surrounding vehicles that contain important status information about a vehicle such as its position, speed, and heading. If an attacker (misbehaving vehicle) injects false position information in a BSM, it can lead to serious consequences including traffic congestion or even accidents. Therefore, it is imperative to accurately detect and identify such attackers to ensure safety in the network. This paper presents a novel data-centric approach to detect <i>position falsification</i> attacks, using machine learning (ML) algorithms. Unlike existing techniques, the proposed approach combines information from 2 consecutive BSMs for training and testing. Simulations using the Vehicular Reference Misbehavior (VeReMi) dataset demonstrate that the proposed model clearly outperforms existing approaches for identifying a range of different attack types.

Misbehavior Detection and Optimal Threshold Analysis in DF Cooperative Relay Networks

In this letter, a detect-before-decode (DbD) method for relay misbehavior detection in a wireless decode-and-forward (DF) cooperative network is proposed. Since this method makes no use of the decoding results, the detection errors caused by erroneously decoding are eliminated. A unified sufficient statistic for relay misbehavior detection, which is applicable to all link outage conditions, is constructed. Furthermore, the closed-form expression of the optimal threshold which minimizes the source-to-destination outage probability is derived. Numerical simulations show that the proposed method outperforms the long-term relay link observing method in terms of false alarm and miss detection rates. It has the same false alarm and miss detection rates as the physical integrity check (PIC) method with lower computational complexity. The outage probability performance is also improved when transmit power is low.

CT2‐MDS: Cooperative trust‐aware tolerant misbehaviour detection system for connected and automated vehicles

Connected and automated vehicles (CAVs) are recognized as a promising solution to improve road safety. Before deploying CAVs, securing the communication environment is a critical challenge. To secure the exchanged sensitive messages between CAVs, a novel cooperative trust-aware tolerant misbehaviour detection system (CT2-MDS) is proposed in this paper. The vehicle-to-everything (V2X) network model in real complex scenarios is built first, and several typical types of attacks are simulated. The cooperative trust factor is then defined to evaluate the received message packet's plausibility instead of the node. And the measuring uncertainty of sensors is considered to improve the overall detection precision. At last, a multi-model fusion misbehaviour detection method is presented based on the idea of cross-validation. In this mechanism, different from the binary classification, the misbehaviour messages are categorized into particular misbehaving classes. To verify the proposed system's performance, the simulation is conducted, and the results showed that the proposed method outperformed existing single classifiers and provided good prediction accuracy in different attack density.

Detecting and Rectifying Vehicle Malicious Misbehavior for Intersection Movement Assist: A Sensor-Based Misbehavior Detection Study

Recent developments in wireless communication technologies have led to the evolution of connectivity between vehicles. Maintaining connectivity between vehicles increases a vehicle’s awareness of other nearby vehicles, which can be used in safety applications. Identification of malicious misbehaving vehicles plays an important role in road safety. This research establishes the minimum detectable error (MDE) boundary for relative position between the observer and status vehicles (SV) using vehicle sensor and GPS error profile from field tests and established minimum standards. The results demonstrated that the MDE increases in the lateral direction (side-to-side) with the increase in relative distance between the observer and status vehicles (OV and SV) while remaining the same in the longitudinal direction (front-to-back). This research effort explores the use of Sensor-Based Misbehavior Detection (SBMD) with current specifications and the defined MDE boundary for implementation in the Intersection Movement Assist (IMA) safety application to rectify false positive and false negative hazard messages propagated by a malicious misbehaving vehicle. The simulation approach used in this research quantifies the total number of false positive/negative hazard detections received by a third-party vehicle (TPV) using the IMA safety application and assesses the capability of the OV equipped with SBMD to rectify the false positive/negative hazard detection. In cases where there was no hazard, SBMD produced an 83% to 90% improvement in the reduction of false positive hazard detections. In the cases with hazard scenario, where the SV is in the not-safe-to-cross zone, SBMD produced an 80% to 99% improvement in application performance.

A review on Detection of Misbehavior in Lane through Traffic Regulatory Application

A review on Detection of Misbehavior in Lane through Traffic Regulatory Application

A Survey of Trust Management in the Internet of Vehicles

Over the past decade, the groundbreaking technological advancements in the Internet of Vehicles (IoV) coupled with the notion of trust have attracted increasing attention from researchers and experts in intelligent transportation systems (ITS), wherein vehicles establish a belief towards their peers in the pursuit of ensuring safe and efficacious traffic flows. Diverse domains have been taking advantage of trust management models in the quest of alleviating diverse insider attacks, wherein messages generated by legitimate users are altered or counterfeited by malicious entities, subsequently, endangering the lives of drivers, passengers, and vulnerable pedestrians. In the course of vehicles forming perceptions towards other participating vehicles, a range of contributing parameters regarding the interactions among these vehicles are accumulated to establish a final opinion towards a target vehicle. The significance of these contributing parameters is typically represented by associating a weighting factor to each contributing attribute. The values assigned to these weighting factors are often set manually, i.e., these values are predefined and do not take into consideration any affecting parameters. Furthermore, a threshold is specified manually that classifies the vehicles into honest and dishonest vehicles relying on the computed trust. Moreover, adversary models as an extension to trust management models in order to tackle the variants of insider attacks are being extensively emphasized in the literature. This paper, therefore, reviews the state of the art in the vehicular trust management focusing on the aforementioned factors such as quantification of weights, quantification of threshold, misbehavior detection, etc. Moreover, an overarching IoV architecture, constituents within the notion of trust, and attacks relating to the IoV have also been presented in addition to open research challenges in the subject domain.

A new procedure for misbehavior detection in vehicular ad-hoc networks using machine learning

Misbehavior detection in vehicular ad hoc networks (VANETs) is performed to improve the traffic safety and driving accuracy. All the nodes in the VANETs communicate to each other through message logs. Malicious nodes in the VANETs can cause inevitable situation by sending message logs with tampered values. In this work, various machine learning algorithms are used to detect the primarily five types of attacks namely, constant attack, constant offset attack, random attack, random offset attack, and eventual attack. Firstly, each attack is detected by different machine learning algorithms using binary classification. Then, the new procedure is created to do the multi classification of the attacks on best chosen algorithm from different machine learning techniques. The highest accuracy in case of binary classification is obtained with Naïve Bayes (100%), decision tree (100%), and random forest (100%) in type1 attack, decision tree (100%) in type2 attack, and random forest (98.03%, 95.56%, and 95.55%) in Type4, Type8 and Type16 attack respectively. In case of new procedure for multi-classification, the highest accuracy is obtained with random forest (97.62%) technique. For this work, VeReMi dataset (a public repository for the malicious node detection in VANETs) is used.

Deep Reinforcement Learning Based Dynamic Reputation Policy in 5G Based Vehicular Communication Networks

Vehicular networks are vulnerable to various attacks from malicious vehicles or infrastructures within a network. The collaborative misbehavior detection system can be used to detect these internal or insider attacks. However, in a collaborative misbehavior detection system, an attacker may lower the detection accuracy by sending false feedback. A trust model can be used to stimulate vehicles to send true feedbacks. However, an attacker can take advantage of weak or strong reputation update methods. A dynamic trust or reputation update policy can be used to stimulate vehicles to send true feedbacks. In this paper, we propose a deep reinforcement learning based dynamic reputation update policy. In the proposed scheme, feedbacks from vehicles are combined in vehicular edge computing (VEC) servers using Dempster-Shafer theory and the results are used to predict the average number of true messages. VEC then uses deep reinforcement learning to determine the optimum reputation update policy to stimulate vehicles to send true feedbacks. In addition, through extensive simulations, we show that the proposed dynamic reputation-policy is better in terms of the average number of true feedbacks compared to the existing reputation update policy.

A Privacy-Preserving Misbehavior Detection System in Vehicular Communication Networks

5 G based vehicular communication networks support various traffic safety and infotainment use cases and rely on the periodic exchange of information. However, these messages are susceptible to several attacks which can be detected using misbehavior detection systems (MDS). MDS utilizes trust score, feedback score and other evaluation schemes to identify abnormal behavior of the vehicles. However, the trust and feedback scores used in MDS may violate the location, trajectory, or identity privacy of the vehicle. In this paper, we propose a privacy-preserving misbehavior detection system that can detect or identify misbehavior without violating the privacy of the vehicle. In the proposed method, encrypted weighted feedbacks sent from vehicles are combined using additive homomorphic properties without violating the privacy of the information. The decryption of the aggregate feedback is done securely at the trusted authority which updates the reputation score of the vehicle according to the decrypted aggregate feedback score. We have also performed comprehensive security analysis and have shown the correctness and resilience of the proposed schemes against various attacks. In addition, we have done extensive performance analysis and have shown that the computation cost of the proposed scheme is better compared to the existing schemes.

Integrated Context-Based Mitigation Framework for Enforcing Security against Rendezvous Point Attack in MANETs

Reliable communication in ad hoc networks necessitates mobile nodes to synchronize among themselves for cooperation. The cooperation in ad hoc networks is enforced through the implementation of encryption algorithms and intrusion detection systems. Most of the intrusion detection and encryption algorithms are not effective enough to address the extent to which a participative mobile node may trust other interacting mobile nodes for data forwarding. The existing mitigation frameworks consider packet forwarding capability as the single parameter for calculating trust values which cannot be appropriate for computing the accurate trust factor as reliable nodes are highly impacted by data rate, throughput, delay and energy consumption. An Integrated Context-based Mitigation Framework (ICMF) is proposed for facilitating effective mitigation of rendezvous point misbehavior and for enhancing the performance of the network. This proposed ICMF framework facilitates rendezvous point misbehavior detection by determining Grey theory Inspired Discriminating Factor (GTIDF) that is contextually derived from multiple factors including data rate, throughput, delay and energy consumptions using the benefits of the Grey theory. From the simulation results of the proposed ICMF framework, improved root node attackers survivability rate and root node attackers categorization rate are inferred when compared to the benchmarked baseline mitigation frameworks.