The DOI matches its Crossref record; 161 of the 170 references it cites were found in a registry or an index; 15 of the 166 sources its claims cite were checked for support.
Security and Trust Management in the Internet of Vehicles (IoV): Challenges and Machine Learning Solutions
Open accessAbstract
The Internet of Vehicles (IoV) is a technology that is connected to the public internet and is a subnetwork of the Internet of Things (IoT) in which vehicles with sensors are connected to a mobile and wireless network. Numerous vehicles, users, things, and networks allow nodes to communicate information with their surroundings via various communication channels. IoV aims to enhance the comfort of driving, improve energy management, secure data transmission, and prevent road accidents. Despite IoV's advantages, it comes with its own set of challenges, particularly in the highly important aspects of security and trust. Trust management is one of the potential security mechanisms aimed at increasing reliability in IoV environments. Protecting IoV environments from diverse attacks poses significant challenges, prompting researchers to explore various technologies for security solutions and trust evaluation methods. Traditional approaches have been employed, but innovative solutions are imperative. Amid these challenges, machine learning (ML) has emerged as a potent solution, leveraging its remarkable advancements to effectively address IoV's security and trust concerns. ML can potentially be utilized as a powerful technology to address security and trust issues in IoV environments. In this survey, we delve into an overview of IoV and trust management, discussing security requirements, challenges, and attacks. Additionally, we introduce a classification scheme for ML techniques and survey ML-based security and trust management schemes. This research provides an overview for understanding IoV and the potential of ML in improving its security framework. Additionally, it provides insights into the future of trust and security enhancement.
Overview
CoChat Summary
TL;DR
This survey reviews security and trust management in the Internet of Vehicles (IoV), covering security requirements, attacks, and traditional versus machine-learning solutions. It argues that supervised, unsupervised, and reinforcement learning can improve IoV security and trust, while identifying real-world testing, unknown attacks, blockchain, big data, and dataset availability as future directions.
Key findings
- The survey classifies IoV security and trust solutions into traditional and ML-based approaches, and reports that ML-based solutions are more widely used than traditional solutions for detecting malicious nodes and attacks in IoV networks.
- Reported ML results include a decision-tree classifier achieving 95% accuracy for vehicle misbehavior detection; kNN and SVM achieving 99% accuracy for malicious node attack detection in VANET; plausibility checks adding 5% precision and 2% recall gains; a random forest IDS classifying over four attack types with an F1 score of 97% and a 4% false-positive rate; an LSTM-based RNN detecting Sybil attacks with 95% accuracy; and XGBoost/Random Forest showing 10% inaccuracy.
- Trust-related ML work includes Bayesian neural networks, kNN for fake position attacks, a Naïve Bayes classification-based trust model, and an IoT dataset adapted from CRAWDAD with 18,226 interactions among 76 nodes, where FM2 was superior at accurately classifying dishonest vehicles.
- The survey identifies security requirements including authentication, confidentiality, availability, data integrity, nonrepudiation, access control, privacy, and real-time guarantees, and discusses attacks such as wormhole, black hole, GPS spoofing, DoS/DDoS, Sybil, man-in-the-middle, masquerading, eavesdropping, and malware.
Methods
- Structured literature review using keywords such as “Internet of Vehicles”, “IoV security”, “IoV trust”, “machine learning”, “ML-based security”, “ML-based trust”, and “IoV challenges”; searched Google Scholar, IEEE Xplore, Springer, MDPI, and the ACM Digital Library.
- Publication date range 2017–2023; inclusion focused on ML-based approaches for addressing security and trust concerns in IoV; after exclusions, 50 publications related to the classification of security and trust solutions for IoV were selected.
- The survey organizes ML techniques into supervised, unsupervised, and reinforcement learning and surveys IoV ML-based security and trust management schemes.
Limitations
- Stated future work/limitations: need real-time/field testing of ML-based security solutions; adaptive ML models for unknown/new attacks; blockchain scalability, performance, and privacy issues; IoV and big data integration; and creation/sharing of open datasets representing real-world vehicular network scenarios.
- The paper states that ML faces challenges including failure in detection of attacks, wrongly classified objects, recognition of driver monitoring patterns, vehicle theft, and compromised functional safety.
- Evident from the provided text: the full text is fragmented, with several section headings empty or truncated, which limits independent verification of some claims; the survey is narrative rather than a quantitative meta-analysis.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures







Verification
Claims the paper makes
14 Valid · 24 Not valid · 103 Not checked · 55 Own results and interpretations
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“In the survey in [66], the security aspect was not covered by the authors.”
§ Security and Trust Management in the Internet of Vehicles (IoV): Challenges and Machine Learning Solutions > 4. Related Surveys
What the sources say
- Disputedcites [66] Wang, 2020, A survey on trust evaluation based on machine learning, ACM Comput. Surv. (CSUR) sourceExperimental — accuracy not yet measured
The survey covers security-related aspects: Section 3.7 compares methods on privacy protection and resistance to attacks, and Section 4.1 explicitly discusses security problems in existing work. This contradicts the claim that the authors did not cover the security aspect. (LLM, conf=0.91)
Checked by a reasoning model — may be wrong.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
Every source the paper cites for this claim was checked and supports it.
In the paper
“ML-based trust evaluations are capable of finding substitute data for the unavailable indirect recommendation and direct historical interaction information in newcomer trustees.”
§ Security and Trust Management in the Internet of Vehicles (IoV): Challenges and Machine Learning Solutions > 4. Related Surveys
What the sources say
- Supportedcites [66] Wang, 2020, A survey on trust evaluation based on machine learning, ACM Comput. Surv. (CSUR) source
Section 2.2 says that direct historical interaction and indirect recommendation information do not exist for newcomer trustees. It explains that ML-based trust evaluation can instead use other available trust-related feature data to build a trust model and evaluate trust. (LLM, conf=0.92)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Highly accurate results can be ensured through the use of ML for trust evaluation in instances in which big data are processed.”
§ Security and Trust Management in the Internet of Vehicles (IoV): Challenges and Machine Learning Solutions > 3. Background > 3.2. Machine Learning
What the sources say
- Partly supportedcites [40] Huang, 2019, Improve reputation evaluation of crowdsourcing participants using multidimensional index and machine learning techniques, IEEE Access sourceExperimental — accuracy not yet measured
The 10-FOLD CROSS-VALIDATION section reports up to 0.96 classification accuracy for the LDA-RF model, and the Conclusion places the crowdsourcing reputation-evaluation model in a big-data environment. This supports high accuracy for a particular ML-based model, but not the claim that ML generally ensures highly accurate trust evaluations whenever big data are processed. (LLM, conf=0.86)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“In [140], the authors proposed an IDS scheme to classify normal and malicious traffic messages in vehicle networks using eight supervised models. Their scheme demonstrated high performance.”
§ Security and Trust Management in the Internet of Vehicles (IoV): Challenges and Machine Learning Solutions > 6. Solutions for Security and Trust in IoV > 6.2. Machine Learning-Based Solutions for Security
What the sources say
- Supportedcites [140] Alalwany, E., and Mahgoub, I. (2022). Classification of Normal and Malicious Traffic Based on an Ensemble of Machine Learning for a Vehicle CAN-Network. Sensors, 22. source
The Introduction states that the proposed IDS uses eight supervised ML algorithms for binary classification of in-vehicle network traffic. Section 4.1.6 identifies the eight classifiers and their normal-versus-malicious message target. Section 5.2 reports successful detection and high binary-classification performance. (LLM, conf=0.93)
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“After implementing these exclusion criteria, 50 publications related to the classification of security and trust solutions for IoV were selected for this review.”
§ Security and Trust Management in the Internet of Vehicles (IoV): Challenges and Machine Learning Solutions > 2. Search Methodology
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
23 more claims
Create a free account to see all 196 claims and to verify the 55 references still open.
- Probably not a substantial claim. 130
- It may state two separate claims as one. 93
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“IoV security has been reviewed by Maoudi et al. [102] and Junejo et al. [103] without an LLM agent lens.”
From Agentic AI and Large Language Models for Autonomous IoT Cybersecurity: A Systematic Survey, Taxonomy, and Research Roadmap (2026) · cites this paper as [103]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Security and Trust Management in the Internet of Vehicles (IoV): Challenges and Machine Learning Solutions > 1. Introduction
“Section 2 provides background information. Section 3 discusses related surveys. Section 4 describes the concept of IoV. Section 5 examines solutions based on ML and traditional approaches for security and trust in IoV. Section 6 concludes the paper.”
§ Security and Trust Management in the Internet of Vehicles (IoV): Challenges and Machine Learning Solutions > 7. Conclusions
“## 7. Conclusions”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Security and Trust Management in the Internet of Vehicles (IoV): Challenges and Machine Learning Solutions > 4. Related Surveys
“For example, the surveys in [50,70,76] addressed the use of ML-based trust evaluation in IoV focusing on the trust scheme.”
§ Security and Trust Management in the Internet of Vehicles (IoV): Challenges and Machine Learning Solutions > 4. Related Surveys
“The challenge of trust in the VANET environment was not discussed. In [50], the authors focused on the proposed ML method for ITS challenges. Security and trust were not addressed”
Cited works that were retracted
Works this paper cites that were later retracted, from the retraction notices publishers deposit. Major when the notice came out before this paper was published.
A note, not an issue: for example, a cited work that was retracted only after this paper was published, which its authors could not have known.
In the paper
“Akanksha, E., Sharma, N., and Gulati, K. (2021, January 8–10). Review on reinforcement learning, research evolution and scope of application. Proceedings of the 2021 5th International Conference on Computing Methodologies and Communication (ICCMC), Erode, India.”
Cited work 10.1109/iccmc51019.2021.9418283 · retracted 2026-06-17 · notice 10.1109/iccmc51019.2021.11570769 · this paper published 2024-01-08
Citations
Cites
1 retracted
Retracted: Review on Reinforcement Learning, Research Evolution and Scope of Application
Akanksha, E., Jyoti, Sharma, N., & Gulati, K. (2021) · 2021 5th International Conference on Computing Methodologies and Communication (ICCMC) · doi:10.1109/iccmc51019.2021.9418283 · Cited by 51
RetractedInternet of Things (IoT): A vision, architectural elements, and future directions
Gubbi, J., Buyya, R., Marusic, S., & Palaniswami, M. (2013) · Future Generation Computer Systems · doi:10.1016/j.future.2013.01.010 · Cited by 12,293
Machine learning: Trends, perspectives, and prospects
Jordan, M. I., & Mitchell, T. M. (2015) · Science · doi:10.1126/science.aaa8415 · Cited by 9,955
A survey of trust and reputation systems for online service provision
Jøsang, A., Ismail, R., & Boyd, C. (2007) · Decision Support Systems · doi:10.1016/j.dss.2005.05.019 · Cited by 3,330
The Internet of Things (IoT): Applications, investments, and challenges for enterprises
Lee, I., & Lee, K. (2015) · Business Horizons · doi:10.1016/j.bushor.2015.03.008 · Cited by 2,803
An empirical comparison of supervised learning algorithms
Caruana, R., & Niculescu-Mizil, A. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143865 · Cited by 2,780
(2012) · elib (German Aerospace Center) · Cited by 1,994
Karagiannis, G., Altintas, O., Ekici, E., Heijenk, G., Jarupan, B., Lin, K., & Weil, T. (2011) · IEEE Communications Surveys & Tutorials · doi:10.1109/surv.2011.061411.00019 · Cited by 1,529
Machine Learning Paradigms for Next-Generation Wireless Networks
Jiang, C., Zhang, H., Ren, Y., Han, Z., Chen, K.-C., & Hanzo, L. (2017) · IEEE Wireless Communications · doi:10.1109/mwc.2016.1500356wc · Cited by 1,095
Internet of vehicles: From intelligent grid to autonomous cars and vehicular clouds
Gerla, M., Lee, E.-K., Pau, G., & Lee, U. (2014) · 2014 IEEE World Forum on Internet of Things (WF-IoT) · doi:10.1109/wf-iot.2014.6803166 · Cited by 828
Research works printed but not linked: 11
- Minhas, 2010, Towards expanded trust management for agents in vehicular ad-hoc networks, Int. J. Comput. Intell. Theory Pract., 5, 3
- Alloghani, M., Al-Jumeily, D., Mustafina, J., Hussain, A., and Aljaaf, A.J. (2020). Supervised and Unsupervised Learning for Data Science, Springer.
- Liu, 2011, Internet of Vehicles: Your next connection, Huawei WinWin, 11, 23
- Wu, W., Yang, Z., and Li, K. (2016). Internet of Things, Elsevier.
- Gür, G., Bahtiyar, Ş., and Alagöz, F. (2015). Modeling and Simulation of Computer Networks and Systems, Elsevier.
- Rawat, 2012, VANET: Security attacks and its possible solutions, J. Inf. Oper. Manag., 3, 301
- Sommer, C., Eckhoff, D., Brummer, A., Buse, D.S., Hagenauer, F., Joerer, S., and Segata, M. (2019). Recent Advances in Network Simulation: The OMNeT++ Environment and Its Ecosystem, Springer.
- Biswas, 2018, Intrusion detection using machine learning: A comparison study, Int. J. Pure Appl. Math., 118, 101
- Singh, P.K., Gupta, R.R., Nandi, S.K., and Nandi, S. (2019). Web, Artificial Intelligence and Network Applications: Proceedings of the Workshops of the 33rd International Conference on Advanced Information Networking and Applications (WAINA-2019), Matsue, Japan, 27–29 March 2019, Springer.
- Lokman, S.F., Othman, A.T., Musa, S., and Abu Bakar, M.H. (2019). Progress in Engineering Technology: Automotive, Energy Generation, Quality Control and Efficiency, Springer.
- Siddiqui, S.A., Mahmood, A., Zhang, W.E., and Sheng, Q.Z. (2019). Neural Information Processing: 26th International Conference, ICONIP 2019, Sydney, NSW, Australia, 12–15 December 2019, Springer.
Cited by
Energy Intelligence: A Systematic Review of Artificial Intelligence for Energy Management
Safari, A., Daneshvar, M., & Anvari‐Moghaddam, A. (2024) · Applied Sciences · doi:10.3390/app142311112 · Cited by 199
Machine Learning-Based Security Solutions for IoT Networks: A Comprehensive Survey
Alfahaid, A., Alalwany, E., Almars, A. M., Alharbi, F., Atlam, E.-S., & Mahgoub, I. (2025) · Sensors · doi:10.3390/s25113341 · Cited by 120
Self-citationVisconti, P., Rausa, G., Del-Valle-Soto, C., Velázquez, R., Cafagna, D., & Fazio, R. D. (2025) · Sensors · doi:10.3390/s25020562 · Cited by 105
An Effective Ensemble Learning-Based Real-Time Intrusion Detection Scheme for an In-Vehicle Network
Alalwany, E., & Mahgoub, I. (2024) · Electronics · doi:10.3390/electronics13050919 · Cited by 37
Self-citationAli, H. I., Kurunathan, H., Eldefrawy, M. H., Gruian, F., & Jönsson, M. (2025) · IEEE Access · doi:10.1109/access.2025.3537800 · Cited by 24
Metadata
- Authors
- Alalwany, E., & Mahgoub, I.
- Affiliations
- Taibah University (SA)
- Florida Atlantic University (US)
- Corresponding author
- Mahgoub, Imad
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2024-01-08
- Volume
- 24
- Issue
- 2
- Pages
- 368
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC10819911
- OpenAlex
- W4390670939
- Cited by
- 130
- References
- 170
- Citations by year
- 2026: 44 · 2025: 64 · 2024: 22
- FWCI
- 2.94
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Florida Atlantic University
- Universidad del Atlántico
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Vehicular Ad Hoc Networks (VANETs)
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Physical Sciences › Computer Science › Computer Networks and Communications › Access Control and Trust
- Keywords
- Internet of Vehicles, trust management, VANET security, machine learning for security, attack classification, trust evaluation, vehicular communication, Internet of Things, security requirements
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Security and Trust Management in the Internet of Vehicles (IoV): Challenges and Machine Learning Solutions. https://app.cochat.ai/papers/10.3390/s24020368
- The paper
- Alalwany, E., & Mahgoub, I. (2024). Security and Trust Management in the Internet of Vehicles (IoV): Challenges and Machine Learning Solutions. Sensors. https://doi.org/10.3390/s24020368
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.