A Deep Learning Based Driver Classification and Trust Computation in VANETs
The DOI matches its Crossref record; 24 of the 25 references it cites were found in a registry or an index.
Abstract
Vehicular ad hoc networks (VANETs) are most promising technology for smart transportation systems to provide road safety. However, VANETs are more vulnerable to malicious nodes and susceptible to a number of security attacks. In order to provide security against these attacks, most of the researchers have presented cryptography based schemes. These schemes ensure legitimate sender but cannot prevent broadcasting bogus message from legitimate sender. Hence, many researchers have proposed trust management based schemes to address internal attacks. However, these schemes encounter with complex iterations and computation overhead. To address these issues, in this paper, a deep learning based driver classification and trust computation (DL-DCTC) scheme is proposed. The sequential Deep Neural Network models are presented to calculate reward-points based on driver behaviour and classify fraudulent and non- fraudulent message/driver. The trust of a vehicle is computed using its reward-points earned during Vehicle to Vehicle (V2V) communications. Extensive simulation results are presented to validate effectiveness of proposed DL-DCTC scheme. The performance analysis showed that proposed scheme's performance is comparatively improved by reduction in computation overhead.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
A Survey on Recent Advances in Vehicular Network Security, Trust, and Privacy
Lu, Z., Qu, G., & Liu, Z. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2018.2818888 · Cited by 608 · cited 1×
“The safety and traffic servies include intersection collision avoidance, vehicle post crash warning, lane changing assistance, traffic and road condition warnings [2].”
BackgroundART: An Attack-Resistant Trust Management Scheme for Securing Vehicular Ad Hoc Networks
Li, W., & Song, H. (2016) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2015.2494017 · Cited by 487 · cited 1×
“In [17], attack-resistant trust management scheme (ART) cope with malicious attacks by evaluating trustworthiness of both vehicles and messages.”
BackgroundOn Data-Centric Trust Establishment in Ephemeral Ad Hoc Networks
Raya, M., Papadimitratos, P., Gligor, V. D., & Hubaux, J.-P. (2008) · IEEE INFOCOM 2008 - The 27th Conference on Computer Communications · doi:10.1109/infocom.2008.180 · Cited by 473
Eviction of Misbehaving and Faulty Nodes in Vehicular Networks
Raya, M., Papadimitratos, P., Aad, I., Jungels, D., & Hubaux, J.-P. (2007) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2007.071006 · Cited by 406 · cited 1×
“[11] have proposed trust management scheme, which relies on infrastructure and makes use of certificates.”
BackgroundTRIP, a trust and reputation infrastructure-based proposal for vehicular ad hoc networks
Gómez Mármol, F., & Martínez Pérez, G. (2012) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2011.03.028 · Cited by 264
A Survey on Trust Management for VANETs
Zhang, J. (2011) · 2011 IEEE International Conference on Advanced Information Networking and Applications · doi:10.1109/aina.2011.86 · Cited by 245 · cited 1×
“hybrid [6].”
A secure authentication scheme for VANETs with batch verification
Bayat, M., Barmshoory, M., Rahimi, M., & Aref, M. R. (2015) · Wireless Networks · doi:10.1007/s11276-014-0881-0 · Cited by 239 · cited 1×
“Later, the proposed scheme is compared with existing schemes [23] and [24] which are denoted in graphs as”
MethodA Reputation-Based Announcement Scheme for VANETs
Li, Q., Malip, A., Martin, K. M., Ng, S.-L., & Zhang, J. (2012) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2012.2209903 · Cited by 203
Trust Management for Vehicular Networks: An Adversary-Oriented Overview
Kerrache, C. A., Calafate, C. T., Cano, J.-C., Lagraa, N., & Manzoni, P. (2016) · IEEE Access · doi:10.1109/access.2016.2645452 · Cited by 194 · cited 1×
“To address this kind of internal attacks, researchers have proposed trust management based security schemes [5].”
BackgroundEfficient Privacy-Preserving Authentication for Vehicular Ad Hoc Networks
Zhu, X., Jiang, S., Wang, L., & Li, H. (2014) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2013.2294032 · Cited by 179 · cited 1×
“Later, the proposed scheme is compared with existing schemes [23] and [24] which are denoted in graphs as”
Method
Cited by
Alalwany, E., & Mahgoub, I. (2024) · Sensors · doi:10.3390/s24020368 · Cited by 130
“In [163], Tangade et al. suggested a trust model that uses deep neural network models (DNN) to improve dependability while simultaneously lowering latency.”
BackgroundMachine Learning for Security in Vehicular Networks: A Comprehensive Survey
Talpur, A., & Gurusamy, M. (2022) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3129079 · Cited by 107
“[61] 2019 Driver behaviour and received messages DL Hybrid trust NA”
BackgroundMethodInfluentialA Survey of Trust Management in the Internet of Vehicles
Siddiqui, S. A., Mahmood, A., Sheng, Q. Z., Suzuki, H., & Ni, W. (2021) · Electronics · doi:10.3390/electronics10182223 · Cited by 89
“Tangade et al. [90] proposed a trust management model that utilizes the notion of deep learning to enhance the reliability and offers reduced latency.”
BackgroundBlockchain-Based Trust Management Model for Vehicular Ad Hoc Networks
Zhao, J., Huang, F., Liao, L., & Zhang, Q. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3318597 · Cited by 82
“The majority of trust-based security schemes currently in use employ intricate iterative procedures, which have the potential to negatively impact VANETs performance and increase network latency [18].”
BackgroundEdge Computing and Deep Learning Enabled Secure Multitier Network for Internet of Vehicles
Grover, H., Alladi, T., Chamola, V., Singh, D., & Choo, K. R. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3071362 · Cited by 80
“A reward-based system for drivers for vehicle-tovehicle communication is presented in [18] which verifies the legitimacy of the messages sent from verified identities.”
BackgroundAssessing Trust Level of a Driverless Car Using Deep Learning
Karmakar, G., Chowdhury, A., Das, R., Kamruzzaman, J., & Islam, S. M. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3059261 · Cited by 72
An Intelligent Intrusion Detection System for 5G-Enabled Internet of Vehicles
Sousa, B., Magaia, N., & Silva, S. (2023) · Electronics · doi:10.3390/electronics12081757 · Cited by 53
“[25] applied DL in vehicular networks, highlighting the possibility of increasing reliability, reducing latency, and detecting security problems.”
MethodWu, Y., Ma, Y., Dai, H., & Wang, H. H. (2020) · Computer Networks · doi:10.1016/j.comnet.2020.107743 · Cited by 51
“In [132], a DL based driver classification and trust computation (DL-DCTC) scheme was proposed.”
MethodTrust management in social Internet of Things across domains
Bangui, H., Bühnová, B., Kušniráková, D., & Halasz, D. (2023) · Internet of Things · doi:10.1016/j.iot.2023.100833 · Cited by 48
Opportunistic UAV Deployment for Intelligent On-Demand IoV Service Management
Sami, H., Saado, R., Saoudi, A. E., Mourad, A., Otrok, H., & Bentahar, J. (2023) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2023.3242205 · Cited by 31
“the trust values from previous behaviors [36], using machine learning [37], and storing the trust values in a secured environment such as a blockchain [38] is out of the scope of this work.”
MethodSocial Internet of Things: Ethical AI Principles in Trust Management
Bangui, H., Bühnová, B., & Ge, M. (2023) · Procedia Computer Science · doi:10.1016/j.procs.2023.03.070 · Cited by 30
On trust management in vehicular ad hoc networks: A comprehensive review
Che, H., Duan, Y., Li, C., & Yu, L. (2022) · Frontiers in the Internet of Things · doi:10.3389/friot.2022.995233 · Cited by 24
“2 AI: Deep learning Deep learning algorithms, particularly deep reinforcement learning algorithms, have received a lot of attention recently and are being used in VANETs (Zhang D. et al., 2018; Tangade et al., 2019; Gyawali et al., 2021; Zhang D. et al., 2022).”
MethodSekhar, B. V. D. S., Udayaraju, P., Kumar, N. U., Sindhuri, K. B., Ramakrishna, B., Babu, B. S., & Srinivas, M. S. S. S. (2022) · Soft Computing · doi:10.1007/s00500-022-07633-4 · Cited by 19
“The authors in Sumra et al. (2015) In Tangade et al. (2019), a deep learning model for finding the best drivers and addressing the issues in the VANET network system is observed.”
RetractedTrust Management Model of VANETs Based on Machine Learning and Active Detection Technology
Huang, F., Li, Q., & Zhao, J. (2022) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/icccworkshops55477.2022.9896700 · Cited by 19
“Most existing trust-based security schemes have complex iterative processes, which will reduce the performance of VANETs and increase the network delay [9].”
BackgroundA Fuzzy Reward and Punishment Scheme for Vehicular Ad Hoc Networks
Shahariar, R., & Phillips, C. (2023) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2023.0140601 · Cited by 7
“Additionally, approaches incentivize trustworthy announcements (positive behaviour) to motivate vehicles to act honestly in the future [3, 6, 8].”
BackgroundPowerTrust: AI-Based Trustworthiness Assessment in the Internet of Grid Things
Ali, W., Din, I. U., Almogren, A., Khan, M. Y., & Altameem, A. (2024) · IEEE Access · doi:10.1109/access.2024.3487617 · Cited by 5
“To detect the behavior of malicious nodes, a hybrid deep learning scheme called DL-based driver-classification-trust-computation (DL-DCTC) is presented in [25].”
MethodA Survey of Security Threats and Trust Management in Vehicular Ad Hoc Networks
Shahariar, R., & Phillips, C. (2025) · Transactions on Engineering and Computing Sciences · doi:10.14738/tmlai.1303.18943 · Cited by 4
“Artificial Intelligence-Based Trust Schemes: Some approaches, for example, [63, 70, 71, 72] employ Artificial Intelligence (AI) to perform the trust computation, for instance, deep learning [73], reinforcement learning [28, 74, 75], decision trees [71, 72] are used for trust management.”
Alam, S., Jameel, A., Parveen, Z., Alnfrawy, E. T., Ashraf, A., Uddin, R., & Aqib, J. (2026) · Machine Learning with Applications · doi:10.1016/j.mlwa.2026.100859 · Cited by 4
“Deep Learning (DL), a subset of ML, models have demonstrated superior capabilities in learning data representations and identifying anomalous patterns (Tangade et al., 2019).”
Bousarhane, B., & Bouzidi, D. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-031-07969-6_2 · Cited by 2
Trust management in the internet of everything: A review of deep-learning based solutions
Bangui, H., Ge, M., & Bühnová, B. (2025) · Internet of Things and Cyber-Physical Systems · doi:10.1016/j.iotcps.2026.03.005 · Cited by 1
Recent Deep Learning Based Trust Solutions
Abasıkeleş‐Turgut, İ., & Altan, G. (2025) · Studies in big data · doi:10.1007/978-3-031-86075-1_1
Impact of Deep Learning on VANET Security: An Analysis
Mana, S. C., Kanmani, A. C., & Chaudhuri, A. (2025) · Studies in computational intelligence · doi:10.1007/978-981-96-5190-0_4
Paranjothi, A. (2023) · SHAREOK (University of Oklahoma; Oklahoma State University; Central Oklahoma University)
Driver Trust Recognition in Suburban Autonomous Driving Scenarios Based on Physiological Signals
Zhang, D., Zhang, M., Li, X., Guo, Z., Zhang, Y., & Li, W. L. W. (2025) · CAA International Conference on Vehicular Control and Intelligence (CVCI) · doi:10.1109/cvci66304.2025.11348410
“In addition, a growing number of studies have started exploring multimodal signal fusion and the incorporation of deep learning techniques as a means to improve the reliability of trust recognition [14], [15].”
Evaluating Granularity in Markov Chain-Based Trust Models for Vehicular Ad Hoc Networks (VANETs)
Shahariar, R. (2026) · Transactions on Engineering and Computing Sciences · doi:10.14738/tmlai.1401.20018
“[11] presents a sequential deep neural network to estimate reward based on the communication of a driver.”
Metadata
- Authors
- Tangade, S., Manvi, S. S., & Hassan, S.
- Affiliations
- REVA University (IN)
- Venue
- 2019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall)
- Publisher
- IEEE
- Published
- 2019-09
- Pages
- 1-6
- ISSN
- 1090-3038 (ISSN-L)
- OpenAlex
- W2984437380
- Semantic Scholar
- 65f93a561b089cecb4d49685d67d6ea702372b78
- Cited by
- 21
- References
- 25
- Citations by year
- 2025: 4 · 2024: 2 · 2023: 6 · 2022: 4 · 2021: 4 · 2020: 1
- FWCI
- 3.58
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Vehicular Technology Conference (publishedVersion)
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Vehicular Ad Hoc Networks (VANETs)
- Physical Sciences › Computer Science › Computer Networks and Communications › Security in Wireless Sensor Networks
- Physical Sciences › Engineering › Automotive Engineering › IoT and GPS-based Vehicle Safety Systems
- Keywords
- vehicular ad hoc networks, driver classification, trust management, malicious node detection, fraud detection, reward points, vehicle-to-vehicle communication, deep neural network, computation overhead reduction, VANET security
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.
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
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.