Highly accurate sybil attack detection in vanet using extreme learning machine with preserved location

Balaram, Allam; Nabi, Shaik Abdul; Rao, Koppula Srinivas; Koppula, Neeraja

doi:10.1007/s11276-023-03399-1

Cited by 9 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These security risks can be categorized into availability, data manipulation, confidentiality, and authentication attacks [14,15]. Such attacks can result in wrong decisions and severe accidents [16,17]. For example, attackers could spread BSMs with falsified location information to affect road safety and management applications, as many rely on accurate position data of surrounding objects [18,19].…”

Section: Introductionmentioning

confidence: 99%

A Machine Learning-based Scheme for Enhancing the Detection of Position Falsification Attacks in Vehicular Ad-Hoc Networks

Abdelkreem,

Hussein,

Tammam

2024

Preprint

View full text Add to dashboard Cite

A vehicular Ad-hoc Network (VANET) is a wireless network established between vehicles and surrounding infrastructure to enable information exchange between them. Consequently, many applications that can enhance passengers' security assurance and traffic flow are built upon this information. However, malicious nodes can manipulate the exchanged data to attack other nodes and disrupt the network’s normal behavior. For example, if an attacker broadcasts a falsified vehicle’s location, the functionality of applications that rely on accurate location sharing will be confused, and deadly accidents may occur. Thus, many studies have been conducted to implement Misbehavior Detection Schemes (MDSs) to identify position spoofing attacks in VANET. However, the performance results of these MDSs are limited in detecting some attack types, and most of them rely on application layer features that the attacker can alter before transmission to evade the detection model. So, this paper proposes an MDS for position falsification attack detection that employs a set of commonly used features besides a physical-layer-based feature called RSSIConf. The RSSIConf feature relies on the Received Signal Strength Indicator of received messages and its confidence intervals at different confidence levels and distances. The evaluations show that the proposed model outperforms existing approaches, where the improvements range between 0.76% to 13.26% in accuracy and 0.74% to 12.71% in F1-Score, depending on the detected attack type.

show abstract

Section: Introductionmentioning

confidence: 99%

A Machine Learning-based Scheme for Enhancing the Detection of Position Falsification Attacks in Vehicular Ad-Hoc Networks

Abdelkreem,

Hussein,

Tammam

2024

Preprint

View full text Add to dashboard Cite

show abstract

Trajectory tracking attack for vehicular ad‐hoc networks

Li,

2024

Security and Privacy

View full text Add to dashboard Cite

Maintaining user privacy and security is a critical concern in vehicular ad hoc networks (VANETs). However, prior research has neglected the study of matrix recovery attack methods in VANETs and the challenge of reducing the number of roadside units (RSUs). In this article, we formulate a path recovery strategy using matrix recovery techniques from an adversarial view. Subsequently, the challenge of minimizing RSUs while monitoring all user vehicles in a region is converted into a set cover problem. We introduce a heuristic algorithm that utilizes clustering to address this issue. To minimize matrix recovery errors, a Kalman filter based method is integrated to enhance the performance. This paper also presents an initial deployment of path recovery attacks, maintaining effectiveness even with certain defense mechanisms in place. Furthermore, we conduct simulation experiments to evaluate the effectiveness of the proposed attack strategy. The simulation results demonstrate the performance across various dimensions. Finally, the results show that the success rate of our proposed counter‐defense strategy in overcoming user defenses surpasses 50%.

show abstract

Unveiling Sybil Attacks Using AI‐Driven Techniques in Software‐Defined Vehicular Networks

Nayak,

Bhoi,

Sahoo

et al. 2024

Security and Privacy

View full text Add to dashboard Cite

The centralized nature of software‐defined networks (SDN) makes them a suitable choice for vehicular networks. This enables numerous vehicles to communicate within an SD‐vehicular network (SDVN) through vehicle‐to‐vehicle (V2V) and with road‐side units (RSUs) via vehicle‐to‐infrastructure (V2I) connections. The increased traffic volume necessitates robust security solutions, particularly for Sybil attacks. Here, the attacker aims to undermine network trust by gaining unauthorized access or manipulating network communication. While traditional cryptography‐based security methods are effective, their encryption and decryption processes may cause excess delays in vehicular scenarios. Previous studies have suggested machine learning (ML) like AI‐driven approaches for Sybil attack detection in vehicular networks. However, the primary drawbacks are high detection time and feature engineering of network data. To overcome these issues, we propose a two‐phase detection framework, in which the first phase utilizes cosine similarity and weighting factors to identify attack misbehavior in vehicles. These metrics contribute to the calculation of effective node trust (ENT), which helps in further attack detection. In the second phase, deep learning (DL) models such as CNN and LSTM are employed for further granular classification of misbehaving vehicles into normal, fault, or Sybil attack vehicles. Due to the time series nature of vehicle data, CNN and LSTM are used. The methodology deployed at the controller provides a comprehensive analysis, offering a single‐ to multi‐stage classification scheme. The classifier identifies six distinct vehicle types associated with such attacks. The proposed schemes demonstrate superior accuracy with an average of 94.49% to 99.94%, surpassing the performance of existing methods.

show abstract

Highly accurate sybil attack detection in vanet using extreme learning machine with preserved location

Cited by 9 publications

References 17 publications

A Machine Learning-based Scheme for Enhancing the Detection of Position Falsification Attacks in Vehicular Ad-Hoc Networks

A Machine Learning-based Scheme for Enhancing the Detection of Position Falsification Attacks in Vehicular Ad-Hoc Networks

Trajectory tracking attack for vehicular ad‐hoc networks

Unveiling Sybil Attacks Using AI‐Driven Techniques in Software‐Defined Vehicular Networks

Contact Info

Product

Resources

About