Trust on wheels: Towards secure and resource efficient IoV networks

Federated Learning with Blockchain Approach for Trust Management in IoV

Connected vehicles are a vital part of smart cities, which connect over a wireless connection and bring mobile computation and communication abilities. As a mediator, fog computing resides between vehicles and the cloud and provides vehicles with processing, storage, and networking power through Vehicular Ad-hoc networks (VANET). VANET is a time-sensitive technology that requires less time to process a request received from a vehicle. Delay and latency are the notorious issues of VANET and fog computing. To deal with such problems, in this work, we developed a priority-based fog computing model for smart urban vehicle transportation that reduces the delay and latency of fog computing. To upgrade the fog computing infrastructure to meet the latency and Quality of Service (QoS) requirements, 5G localized Multi-Access Edge Computing (MEC) servers have also been used, which resulted tremendously in reducing the delay and the latency. We decreased the data latency by 20% compared to the experiment carried using only cloud computing architecture. We also reduced the processing delay by 35% compared with the utilization of cloud computing architecture.

https://www.mdpi.com/2076-3417/12/4/2083/pdf?version=1645413280

A Fog Computing Model for VANET to Reduce Latency and Delay Using 5G Network in Smart City Transportation

A resilient Trust Management framework towards trust related attacks in the Social Internet of Things

As a part of the intelligent transportation system, vehicular ad hoc networks (VANETs) provide timely information about road events and traffic to improve road safety and traffic efficiency. However, VANETs face many challenges, such as attacks from malicious vehicles, identity privacy leakage, and the absence of trust between vehicular nodes. In addition, vehicles nearby an event usually lack the motivation to participate in the traffic event validation whenever it occurs, which requires the cooperation of vehicles on the network. To solve these problems, a blockchain-enabled incentive trust model with a privacy-preserving threshold ring signature scheme for VANETs is proposed. Firstly, a threshold ring signature scheme is designed in order to allow participants in the non-trusted environment to anonymously witness the message’s authenticity and reliability while guaranteeing the vehicle’s privacy. Second, a blockchain-enabled incentive trust management model is presented to enable the roadside units (RSUs) to thwart various attacks and guarantee the trustworthiness of event messages transmitted in VANETs and also motivate the senders of the traffic information and their witnesses with incentives. Finally, to improve efficiency, a practical Byzantine fault-tolerant consensus mechanism is used. Our proposed system is demonstrated to be effective and secure for VANETs, according to both security analysis and performance evaluation.

/pdf/a-blockchain-enabled-incentive-trust-management-with-2la180fc.pdf

A Blockchain-Enabled Incentive Trust Management with Threshold Ring Signature Scheme for Traffic Event Validation in VANETs

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 Survey of Trust Management in the Internet of Vehicles

Deep Neural Networks (DNNs) have gained significant popularity in various Natural Language Processing tasks. However, the lack of interpretability of DNNs induces challenges to evaluate the robustness of DNNs. In this paper, we particularly focus on DNNs on sentiment analysis and conduct an empirical investigation on the sensitivity of DNNs. Specifically, we apply a scoring function to rank words importance without depending on the parameters or structure of the deep neural model. Then, we scan characteristics of these words to identify the model’s weakness and perturb words to craft targeted attacks that exploit this weakness. We conduct extensive experiments on different neural network models across several real-world datasets. We report four intriguing findings: i) modern deep learning models for sentiment analysis ignore important sentiment terms such as opinion adjectives (i.e., amazing or terrible), ii) adjective words contribute to fooling sentiment analysis models more than other Parts-of-Speech (POS) categories, iii) changing or removing up to 10 adjectives words in a review text only decreases the accuracy up to 2%, and iv) modern models are unable to recognize the difference between an objective and a subjective review text1.

Analyzing the Sensitivity of Deep Neural Networks for Sentiment Analysis: A Scoring Approach

Deep Neural Networks (DNNs) have achieved remarkable results in multiple Natural Language Processing (NLP) applications. However, current studies have found that DNNs can be fooled when using modified samples, namely adversarial examples. This work, specifically, examines DNNs for sentiment analysis using adversarial examples. We particularly aim to examine the impact of modifying the Part-Of-Speech (POS) of words on the input sentences. We conduct extensive experiments on different neural network models across several real-world datasets. The results demonstrate that current DNN models for sentiment analysis are brittle with perturbed noisy words that humans do not have trouble understanding. An interesting finding is that adjective words (Adj) and the combination of adjective and adverb words (Adj-Adv) provide obvious contribution to fooling sentiment analysis DNN models1.

Quan Z Sheng

Papers

A Survey of Trust Management in the Internet of Vehicles

Analyzing the Sensitivity of Deep Neural Networks for Sentiment Analysis: A Scoring Approach

Are Modern Deep Learning Models for Sentiment Analysis Brittleƒ An Examination on Part-of-Speech