Novel Deep Learning-Enabled LSTM Autoencoder Architecture for Discovering Anomalous Events From Intelligent Transportation Systems
The DOI matches its Crossref record; 41 of the 42 references it cites were found in a registry or an index.
Abstract
Intelligent Transportation Systems (ITS), especially Autonomous Vehicles (AVs), are vulnerable to security and safety issues that threaten the lives of the people. Unlike manual vehicles, the security of communications and computing components of AVs can be compromised using advanced hacking techniques, thus barring AVs from the effective use in our routine lives. Once manual vehicles are connected to the Internet, called the Internet of Vehicles (IoVs), it would be exploited by cyber-attacks, like denial of service, sniffing, distributed denial of service, spoofing and replay attacks. In this article, we present a deep learning-based Intrusion Detection System (IDS) for ITS, in particular, to discover suspicious network activity of In-Vehicles Networks (IVN), vehicles to vehicles (V2V) communications and vehicles to infrastructure (V2I) networks. A Deep Learning architecture-based Long-Short Term Memory (LSTM) autoencoder algorithm is designed to recognize intrusive events from the central network gateways of AVs. The proposed IDS is evaluated using two benchmark datasets, i.e., the car hacking dataset for in-vehicle communications and the UNSW-NB15 dataset for external network communications. The experimental results demonstrated that our proposed system achieved over a 99% accuracy for detecting all types of attacks on the car hacking dataset and a 98% accuracy on the UNSW-NB15 dataset, outperforming other eight intrusion detection techniques.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Elman, J. L. (1990) · Cognitive Science · doi:10.1207/s15516709cog1402_1 · Cited by 11,212
Moustafa, N., & Slay, J. (2015) · 2015 Military Communications and Information Systems Conference (MilCIS) · doi:10.1109/milcis.2015.7348942 · Cited by 4,033
Self-citationAuto-association by multilayer perceptrons and singular value decomposition
Bourlard, H., & Kamp, Y. (1988) · Biological Cybernetics · doi:10.1007/bf00332918 · Cited by 1,345
Moustafa, N., & Slay, J. (2016) · Information Security Journal: A Global Perspective · doi:10.1080/19393555.2015.1125974 · Cited by 1,100
Self-citationIntrusion Detection System Using Deep Neural Network for In-Vehicle Network Security
Kang, M.-J., & Kang, J.-W. (2016) · PLOS ONE · doi:10.1371/journal.pone.0155781 · Cited by 678
Handbook of Beta Distribution and Its Applications
(2004) · CRC Press eBooks · doi:10.1201/9781482276596 · Cited by 644
In-vehicle network intrusion detection using deep convolutional neural network
Song, H. M., Woo, J., & Kim, H. K. (2020) · Vehicular Communications · doi:10.1016/j.vehcom.2019.100198 · Cited by 586
GIDS: GAN based Intrusion Detection System for In-Vehicle Network
Seo, E., Song, H. M., & Kim, H. K. (2018) · 2018 16th Annual Conference on Privacy, Security and Trust (PST) · doi:10.1109/pst.2018.8514157 · Cited by 533
Anomaly Detection in Automobile Control Network Data with Long Short-Term Memory Networks
Taylor, A., Leblanc, S., & Japkowicz, N. (2016) · 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa.2016.20 · Cited by 400
Research works printed but not linked: 3
- moustaf, 2015, Creating novel features to anomaly network detection using DARPA-2009 data set, Proc 14th Eur Conf Cyber Warfare Secur, 204
- nie, 2017, Free-Fall Hacking Tesla from Wireless to Can Bus, 1
- miller, 2015, Remote exploitation of an unaltered passenger vehicle, 91
Cited by
MTH-IDS: A Multitiered Hybrid Intrusion Detection System for Internet of Vehicles
Yang, L., Moubayed, A., & Shami, A. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3084796 · Cited by 416
“The IDS proposed in [19] is the only research that considers both CAN bus and external networks, and the IDS proposed in [20] is the only technique that can detect both known and unknown attacks.”
BackgroundMethodInfluentialDeep Learning Based Attack Detection for Cyber-Physical System Cybersecurity: A Survey
Zhang, J., Pan, L., Han, Q.-L., Chen, C., Wen, S., & Xiang, Y. (2022) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2021.1004261 · Cited by 432
Design and Development of RNN Anomaly Detection Model for IoT Networks
Ullah, I., & Mahmoud, Q. H. (2022) · IEEE Access · doi:10.1109/access.2022.3176317 · Cited by 270
“…UNSW-NB15 Binary Acc=97.17 [50] SNN BoT-IoT Multiclass Acc=98.73 [48] RNN BoT-IoT Binary Acc=98.31 [51] DSSTE+LSTM NSLKDD Multiclass Acc=81.78 [52] LSTM Autoencoder UNSW-NB15 Binary Acc=98.00 [53] LSTM CIC-IDS2018 Multiclass Acc=94.00 [54] LSTM CICIDS2017 Binary Acc=99.55 [55] BiLSTM KDD…”
BackgroundInfluentialAI-Based Intrusion Detection Systems for In-Vehicle Networks: A Survey
Rajapaksha, S., Kalutarage, H., Al-Kadri, M. O., Petrovski, A., Madzudzo, G., & Cheah, M. (2023) · ACM Computing Surveys · doi:10.1145/3570954 · Cited by 244
“The LSTM autoencoder-based model proposed by Ashraf et al. [12] also used the HCRL CH dataset.”
MethodIntelligent transportation system for internet of vehicles based vehicular networks for smart cities
Rani, P., & Sharma, R. (2023) · Computers and Electrical Engineering · doi:10.1016/j.compeleceng.2022.108543 · Cited by 237
Oseni, A., Moustafa, N., Creech, G., Sohrabi, N., Strelzoff, A., Tari, Z., & Linkov, I. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3188671 · Cited by 192
“In addition, due to the complexity and heterogeneity of IoT-enabled transportation networks, DL-based intrusion detection systems with explainable capability can provide transparency into how cyber-attacks are predicted [5].”
BackgroundSelf-citationAshraf, J., Keshk, M., Moustafa, N., Abdel-Basset, M., Khurshid, H., Bakhshi, A. D., & Mostafa, R. R. (2021) · Sustainable Cities and Society · doi:10.1016/j.scs.2021.103041 · Cited by 194
Self-citationNwakanma, C. I., Ahakonye, L. A. C., Njoku, J. N., Odirichukwu, J. C., Okolie, S. A., Uzondu, C., Ndubuisi Nweke, C. C., & Kim, D.-S. (2023) · Applied Sciences · doi:10.3390/app13031252 · Cited by 202
Boualouache, A., & Engel, T. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3236448 · Cited by 167
“[179] proposed unsupervised learning-based”
Bhavsar, M., Bekele, Y. B., Roy, K., Kelly, J. C., & Limbrick, D. B. (2024) · IEEE Access · doi:10.1109/access.2024.3386631 · Cited by 203
“Additionally, the growing complexity of intelligent connected vehicle systems and the proliferation of external interfaces make vehicle networks more susceptible to cyberattacks [27].”
BackgroundA New Explainable Deep Learning Framework for Cyber Threat Discovery in Industrial IoT Networks
Khan, I. A., Moustafa, N., Pi, D., Sallam, K. M., Zomaya, A. Y., & Li, B. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3130156 · Cited by 154
Self-citationAlmehdhar, M., Albaseer, A. M., Khan, M. A., Abdallah, M. M., Menouar, H., Al-Kuwari, S. M., & Al‐Fuqaha, A. (2024) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2024.3422253 · Cited by 183
“…using gathered CAN frames obtained during vehicle operation under various environmental conditions, encompassing urban and highway settings. a NIDS framework outlined in [157] employs the LSTM autoencoder technique to address security breaches arising at the primary gateways of vehicular systems.”
MethodDuan, G., Lv, H., Wang, H., & Feng, G. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3228493 · Cited by 174
“Others have addressed the application of intrusion detection methods in specific fields, such as the Internet of Vehicles [17], [19], smart metering [20], [21] and the IIoT [5], [22], [23].”
BackgroundAdvanced Learning Technologies for Intelligent Transportation Systems: Prospects and Challenges
Khalil, R. A., Safelnasr, Z., Yemane, N., Kedir, M., Shafiqurrahman, A., & Saeed, N. (2024) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2024.3369691 · Cited by 168
“It also allows transportation agencies to generate vehicle-type specific traffic metrics for better congestion monitoring and analysis of road usage patterns [93], [94], [95].”
BackgroundHDL-IDS: A Hybrid Deep Learning Architecture for Intrusion Detection in the Internet of Vehicles
Ullah, S., Khan, M. A., Ahmad, J. E., Jamal, S. S., Huma, Z. E., Hassan, M. T., Pitropakis, N., Ali, A., & Buchanan, W. J. (2022) · Sensors · doi:10.3390/s22041340 · Cited by 146
“[34] presented a DL-based IDS for intelligent transportation systems (ITS) that learns the behaviour of regular network traffic in an intra-vehicle network, V2V communications, and V2I networks.”
BackgroundMethodKhan, I. A., Moustafa, N., Pi, D., Haider, W., Li, B., & Jolfaei, A. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3105834 · Cited by 143
“Recently, the authors of [25] proposed an IDS based on DL to detect attacks in AVs.”
BackgroundMethodSelf-citationIntrusion Detection in the Automotive Domain: A Comprehensive Review
Lampe, B., & Meng, W. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3309864 · Cited by 140
Federated Learning-Based Misbehavior Detection for the 5G-Enabled Internet of Vehicles
Rani, P., Sharma, C., Ramesh, J. V. N., Verma, S., Sharma, R., Alkhayyat, A. H., & Kumar, S. (2023) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2023.3328020 · Cited by 144
“To validate the performance of the proposed scheme, we compare the results with existing techniques such as GIDS [18], deep learning-based IDS [67], FED-IDS [68], and divisibility in terms of devices and malware samples, the CIC-IDS2017, ISCXIDS2012, Car-Hacking and CSE-CIC-IDS2018 datasets have…”
MethodNovelADS: A Novel Anomaly Detection System for Intra-Vehicular Networks
Agrawal, K., Alladi, T., Agrawal, A., Chamola, V., & Benslimane, A. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3146024 · Cited by 117
“Firstly, it is a complete end-to-end approach with no need to extract manual features, which is in contrast to the approach proposed by Ashraf et al. [14].”
BackgroundMethodResultInfluentialVANET Network Traffic Anomaly Detection Using GRU-Based Deep Learning Model
AlMahadin, G., Aoudni, Y., Shabaz, M., Agrawal, A. V., Yasmin, G., Alomari, E. S., Al‐Khafaji, H. M. R., Dansana, D., & Maaliw, R. R., III (2023) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2023.3326384 · Cited by 116
P2SF-IoV: A Privacy-Preservation-Based Secured Framework for Internet of Vehicles
Kumar, R., Kumar, P., Tripathi, R., Gupta, G. P., & Kumar, N. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3102581 · Cited by 111
“V2X can connect to various other IoT devices with the availability of several modes of wireless connectivity [3].”
BackgroundMethodInfluentialA federated learning framework for cyberattack detection in vehicular sensor networks
Driss, M., Almomani, I., Huma, Z. E., & Ahmad, J. E. (2022) · Complex & Intelligent Systems · doi:10.1007/s40747-022-00705-w · Cited by 116
“[14] 2020 LSTM autoencoder algorithm 99.”
MethodSurveying neuro-symbolic approaches for reliable artificial intelligence of things
Lu, Z., Afridi, I. U., Kang, H. J., Ruchkin, I., & Zheng, X. (2024) · Journal of Reliable Intelligent Environments · doi:10.1007/s40860-024-00231-1 · Cited by 130
Saheed, Y. K., & Chukwuere, J. E. (2024) · Results in Engineering · doi:10.1016/j.rineng.2024.103171 · Cited by 121
Machine learning and blockchain technologies for cybersecurity in connected vehicles
Ahmad, J., Zia, M. U., Naqvi, I. H., Chattha, J. N., Butt, F. A., Huang, T., & Xiang, W. (2023) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.1515 · Cited by 120
“Ashraf et al. (2021) and Hossain et al. (2020) used the long-short-term memory (LSTM) autoencoder technique which is a recurrent neural network (RNN) architecture.”
MethodHoang, T.-N., & Kim, D. (2022) · Vehicular Communications · doi:10.1016/j.vehcom.2022.100520 · Cited by 117
IADF-CPS: Intelligent Anomaly Detection Framework towards Cyber Physical Systems
Nagarajan, S. M., Devarajan, G. G., Bashir, A. K., Mahapatra, R. P., & Al-Numay, M. S. (2022) · Computer Communications · doi:10.1016/j.comcom.2022.02.022 · Cited by 92
Roadmap for Cybersecurity in Autonomous Vehicles
Kukkala, V. K., Thiruloga, S. V., & Pasricha, S. (2022) · IEEE Consumer Electronics Magazine · doi:10.1109/mce.2022.3154346 · Cited by 106
“…CNNs to detect attacks aimed at RSUs CS-IDS [20] DBN for data reduction; DT classifier to detect attacks in received cloud service requests AED-ITS [22] LSTM based autoencoder; static threshold to detect V2V and V2I attacks A summary of both in-vehicle network and VANET level IDSs discussed in…”
LCCDE: A Decision-Based Ensemble Framework for Intrusion Detection in The Internet of Vehicles
Yang, L., Shami, A. A., Stevens, G., & de Rusett, S. (2022) · Globecom · doi:10.1109/globecom48099.2022.10001280 · Cited by 89
“Tables II and III also compare the performance of the proposed technique with existing state-of-the-art methods [14] [16] [18] [19] [23] [24] on the two datasets.”
MethodYamany, W., Moustafa, N., & Turnbull, B. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3130906 · Cited by 103
“number of drivers, reduce accident rates and transportation expenses, and provide greater flexibility for traffic management [1].”
BackgroundSelf-citationShahriar, M. H., Xiao, Y., Moriano, P., Lou, W., & Hou, Y. T. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3303271 · Cited by 88
“Other research efforts also proposed the RNN/LSTM-based models with an embedding layer working on CAN payload values in [47], [74], and [75].”
BackgroundMethodCyber Attack Detection for Self-Driving Vehicle Networks Using Deep Autoencoder Algorithms
Alsaade, F. W., & Al-Adhaileh, M. H. (2023) · Sensors · doi:10.3390/s23084086 · Cited by 95
“[51] and applied in the setting of maritime transportation systems, which is a relevant field of study.”
BackgroundMethodLBDMIDS: LSTM Based Deep Learning Model for Intrusion Detection Systems for IoT Networks
Saurabh, K., Sood, S., Kumar, P. A., Singh, U., Vyas, R., Vyas, O. P., & Khondoker, R. (2022) · IEEE World AI IoT Congress (AIIoT) · doi:10.1109/aiiot54504.2022.9817245 · Cited by 94
A systematic survey of attack detection and prevention in Connected and Autonomous Vehicles
Limbasiya, T., Teng, K. Z., Chattopadhyay, S., & Zhou, J. (2022) · Vehicular Communications · doi:10.1016/j.vehcom.2022.100515 · Cited by 102
An Investigation of Cyber-Attacks and Security Mechanisms for Connected and Autonomous Vehicles
Gupta, S., Maple, C. R., & Passerone, R. (2023) · IEEE Access · doi:10.1109/access.2023.3307473 · Cited by 96
“[81] describe a statistical feature extraction technique to acquire contextual features from network traffic that can be exploited by IDS for IoVs.”
MethodSupervised contrastive ResNet and transfer learning for the in-vehicle intrusion detection system
Hoang, T.-N., & Kim, D. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122181 · Cited by 87
Korba, A. A., Boualouache, A., & Ghamri-Doudane, Y. M. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3385916 · Cited by 86
“The testing phase functions g 0 and f φ (lines [7–9]) also operate in O ( N ) , independent of the dataset size, with N being the test sample size.”
BackgroundMethodZuo, Z., Ma, L., Liang, S., Liang, J., Zhang, H., & Liu, T. (2022) · Process Safety and Environmental Protection · doi:10.1016/j.psep.2022.06.036 · Cited by 74
Almutlaq, S., Derhab, A., Hassan, M. M., & Kaur, K. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3202869 · Cited by 82
“They can be deployed to identify these attacks when the preventive countermeasures fail by monitoring host and network activities [2], [3], [4].”
BackgroundJin, F., Chen, M., Zhang, W., Yuan, Y., & Wang, S. (2021) · Information Sciences · doi:10.1016/j.ins.2021.08.010 · Cited by 75
Abirami, S., Manickaraj, P., Uthayakumar, M., & Chitra, P. (2024) · Case Studies on Transport Policy · doi:10.1016/j.cstp.2024.101247 · Cited by 76
An Efficient Intrusion Prevention System for CAN: Hindering Cyber-Attacks With a Low-Cost Platform
de Araujo-Filho, P. F., Pinheiro, A. J., Kaddoum, G., Campelo, D. R. D. S., & Soares, F. L. (2021) · IEEE Access · doi:10.1109/access.2021.3136147 · Cited by 71
“Due to their lack of security in vehicles and their widespread and ever-increasing connectivity capabilities, automotive CANs can be accessed through different types of communication interfaces [3], [37].”
BackgroundMethodCAN Bus Intrusion Detection Based on Auxiliary Classifier GAN and Out-of-distribution Detection
Zhao, Q., Chen, M., Gu, Z., Luan, S., Zeng, H., & Chakrabory, S. (2022) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3540198 · Cited by 70
“[5] present an LSTM-based autoencoder, and use a statistical feature extraction technique to capture contextual features as input, instead of using the raw message bits as input.”
BackgroundMethodInfluentialTime-Series Anomaly Detection in Automated Vehicles Using D-CNN-LSTM Autoencoder
Khanmohammadi, F., & Azmi, R. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3380263 · Cited by 61
“Detection System (IDS) for handling time series data to find out anomalous events from ITS [39].”
BackgroundDiffTAD: Denoising diffusion probabilistic models for vehicle trajectory anomaly detection
Li, C., Feng, G., Li, Y., Liu, R., Miao, Q., & Chang, L. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111387 · Cited by 69
Secure Operations of Connected and Autonomous Vehicles
Han, J., Ju, Z., Chen, X., Yang, M., Zhang, H., & Huai, R. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3304762 · Cited by 67
Convolutional-LSTM networks and generalization in forecasting of household photovoltaic generation
Costa, R. L. D. C. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105458 · Cited by 62
Machine Learning based intrusion detection systems for connected autonomous vehicles: A survey
Nagarajan, J., Mansourian, P., Shahid, M. A., Jaekel, A., Saini, I., Zhang, N., & Kneppers, M. (2023) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-023-01508-7 · Cited by 59
“UNSW-NB15 is used in [140] and [69] as the evaluation method of their proposed IDS for VANET.”
MethodGou, W., Zhang, H., & Zhang, R. (2023) · Sensors · doi:10.3390/s23218788 · Cited by 59
“We primarily focus on the detection of known threats, with a specific emphasis on achieving a highly accurate and efficient multiclass classification of network traffic in IoV.”
BackgroundMethodA Security-by-Design Decision-Making Model for Risk Management in Autonomous Vehicles
Abdel‐Basset, M., Gamal, A., Moustafa, N., Abdel-Monem, A., & El-Saber, N. (2021) · IEEE Access · doi:10.1109/access.2021.3098675 · Cited by 54
Self-citationKumar, R., Kumar, P., Tripathi, R., Gupta, G. P., Garg, S., & Hassan, M. M. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3122021 · Cited by 50
“Ashraf et al. [16] proposed a DL-based long-short term memory autoencoder (LSTM-AE) for intrusion detection in ITS.”
BackgroundEthical Considerations in AI-Based Cybersecurity
Kaushik, K., Khan, A., Kumari, A., Sharma, I., & Dubey, R. (2024) · Blockchain technologies · doi:10.1007/978-981-97-1249-6_19 · Cited by 65
Rajkumar, Y., & Kumar, S. V. N. S. (2024) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-024-01627-9 · Cited by 54
Ahmad, H., Gulzar, M. M., Aziz, S., Habib, S., & Ahmed, I. (2024) · Internet of Things · doi:10.1016/j.iot.2024.101245 · Cited by 50
IoV-BCFL: An intrusion detection method for IoV based on blockchain and federated learning
Xie, N., Zhang, C., Yuan, Q., Kong, J., & Di, X. (2024) · Ad Hoc Networks · doi:10.1016/j.adhoc.2024.103590 · Cited by 52
MEMBER: A multi-task learning model with hybrid deep features for network intrusion detection
Lan, J., Liu, X., Li, B., Sun, J., Li, B., & Zhao, J. W. (2022) · Computers & Security · doi:10.1016/j.cose.2022.102919 · Cited by 49
Optimized detection of cyber-attacks on IoT networks via hybrid deep learning models
Bensaoud, A., & Kalita, J. K. (2025) · Ad Hoc Networks · doi:10.1016/j.adhoc.2025.103770 · Cited by 54
Koroniotis, N., Moustafa, N., Schiliro, F., Gauravaram, P., & Janicke, H. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3106378 · Cited by 45
“Augmentations enabled by the IIoT have already been demonstrated in various maritime and transportation smart environments [5]–[7], leading to the design of intelligent maritime and transportation systems.”
BackgroundSelf-citationA hybrid machine learning model for detecting cybersecurity threats in IoT applications
Usoh, M., Asuquo, P. M., Ozuomba, S., Stephen, B. U.-A., & Inyang, U. G. (2023) · International Journal of Information Technology · doi:10.1007/s41870-023-01367-8 · Cited by 63
“[21]/2020 Car hacking dataset(99%) and UNSW-NB15 (98%)”
Luo, F., Wang, J., Zhang, X., Jiang, Y., Li, Z., & Luo, C. (2023) · PeerJ Computer Science · doi:10.7717/peerj-cs.1648 · Cited by 52
“The necessary experiments indicated that with the assistance of the mobile edge, their IDS approach reaches 0.9 detection accuracy, and a CAN message detection is completed in an average of 0.61 ms.”
MethodInfluentialAnis, F. M., Alabdullatif, M., Aljbli, S., & Hammoudeh, M. A. A. (2025) · IEEE Access · doi:10.1109/access.2025.3624952 · Cited by 51
“RNNs, including Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) variants, capture temporal dependencies in packet or flow sequences; LSTM-based autoencoders and classifiers achieved strong results in both IoT and vehicular IDS applications [25].”
Wang, Z., Tian, J., Qin, J., Fang, H., & Chen, L. (2021) · Computational Intelligence and Neuroscience · doi:10.1155/2021/7126913 · Cited by 47
“UNSW_NB15 2020 Deep learning-enabled LSTM autoencoder [55] LSTM+ autoencoder 96.”
MethodKunang, Y. N., Nurmaini, S., Stiawan, D., & Suprapto, B. Y. (2024) · International Journal of Information Security · doi:10.1007/s10207-023-00807-7 · Cited by 45
Using Machine Learning for Dynamic Authentication in Telehealth: A Tutorial
Fard, S. M. H., Gebali, F., & Mamun, M. (2022) · Sensors · doi:10.3390/s22197655 · Cited by 49
“LSTM [69,70,86] LSTM Autoencoder [90] Hybrid Semi-supervised [92] Blockchain-based DRL [94]”
BackgroundMethodDing, W., Alrashdi, I., Hawash, H., & Abdel‐Basset, M. (2023) · Information Sciences · doi:10.1016/j.ins.2023.120057 · Cited by 44
Online transportation network cyber-attack detection based on stationary sensor data
Sun, R., Luo, Q., & Chen, Y. (2023) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2023.104058 · Cited by 40
Evaluation and Selection Models for Ensemble Intrusion Detection Systems in IoT
Alghamdi, R., & Bellaïche, M. (2022) · IoT · doi:10.3390/iot3020017 · Cited by 40
“However, an individual model’s performance sometimes overcomes such an approach, but it is guaranteed that the ensemble approach will decrease the total risk of invalid selection [4].”
BackgroundIoV security and privacy survey: issues, countermeasures, and challenges
Haddaji, A., Ayed, S., & Fourati, L. C. (2024) · The Journal of Supercomputing · doi:10.1007/s11227-024-06269-5 · Cited by 35
CANival: A multimodal approach to intrusion detection on the vehicle CAN bus
Kang, H., Vo, T., Kim, H. K., & Hong, J. B. (2024) · Vehicular Communications · doi:10.1016/j.vehcom.2024.100845 · Cited by 34
Cybersecurity in Connected and Autonomous Vehicles: A Systematic Review of Automotive Security
Abreu, R., Branco, F., Reis, M. J. C. S., & Serôdio, C. (2025) · IEEE Access · doi:10.1109/access.2025.3584649 · Cited by 39
“On the other hand, Aloqaily et al. [42] and Ashraf et al. [55] proposed hybrid models that combined traditional security mechanisms with AI to improve computational efficiency.”
Le, T.-D., Truong, H. B. H., Pham, V. P., & Kim, D. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112091 · Cited by 33
Ribeiro, D. A., Carrillo, D., Saadi, M., Rosa, R. L., & Rodríguez, D. Z. (2022) · Physical Communication · doi:10.1016/j.phycom.2022.101938 · Cited by 46
Xing, L., Wang, K., Wu, H., Ma, H., & Zhang, X. (2023) · Electronics · doi:10.3390/electronics12102284 · Cited by 36
Blockchain based federated learning for intrusion detection for Internet of Things
Sun, N., Wang, W., Tong, Y., & Liu, K. (2023) · Frontiers of Computer Science · doi:10.1007/s11704-023-3026-8 · Cited by 35
AI-based Intrusion Detection for Intelligence Internet of Vehicles
Man, D., Zeng, F., Lv, J., Xuan, S., Yang, W., & Guizani, M. (2021) · IEEE Consumer Electronics Magazine · doi:10.1109/mce.2021.3137790 · Cited by 32
“17 Ashraf et al. 5 designed an LSTM autoencoding algorithm to identify multiple types of intrusion events from IoV networks.”
MethodCANPerFL: Improve In-Vehicle Intrusion Detection Performance by Sharing Knowledge
Hoang, T.-N., Islam, M. R., Yim, K., & Kim, D. (2023) · Applied Sciences · doi:10.3390/app13116369 · Cited by 30
An Ensemble-Based Hybrid Model for the Detection of Attacks in the Internet of Vehicular Things
Ullah, I., Khalil, I., Bai, X., Garg, S., Kaddoum, G., & Hossain, M. S. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3547999 · Cited by 36
Secure Intrusion Detection by Differentially Private Federated Learning for Inter-Vehicle Networks
Xu, Q., Zhang, L., Ou, D., & Yu, W. (2023) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981231159118 · Cited by 30
Toward Generative AI-Based Intrusion Detection Systems for the Internet of Vehicles (IoV)
Mahmoudi, I., Boubiche, D. E., Athmani, S., Toral-Cruz, H., & Chan-Puc, F. I. (2025) · Future Internet · doi:10.3390/fi17070310 · Cited by 31
“Ashraf et al. [52] designed an LSTM-based autoencoding algorithm to detect multiple intrusion types in IoV networks.”
HDFEF: A hierarchical and dynamic feature extraction framework for intrusion detection systems
Li, Y., Qin, T., Huang, Y., Lan, J., Liang, Z., & Geng, T. (2022) · Computers & Security · doi:10.1016/j.cose.2022.102842 · Cited by 28
Altalbe, A. A. (2023) · IEEE Access · doi:10.1109/access.2023.3347619 · Cited by 25
AlShathri, S. I., Sayed, A., & Hemdan, E. E. (2024) · World Electric Vehicle Journal · doi:10.3390/wevj15080356 · Cited by 25
“Similarly, Ashraf et al. [16] presented a deep learning-based Intrusion Detection System (IDS) specifically designed for ITS to detect suspicious network activity in In-Vehicles Networks (IVN), vehicles-to-vehicles (V2V) communications, and vehicles-to-infrastructure (V2I) networks.”
BackgroundIntrusion Detection System for SDN-enabled IoT Networks using Machine Learning Techniques
Ashraf, J., Moustafa, N., Bukhshi, A. D., & Javed, A. (2021) · 2021 IEEE 25th International Enterprise Distributed Object Computing Workshop (EDOCW) · doi:10.1109/edocw52865.2021.00031 · Cited by 19
Self-citationXing, L., Wang, K., Wu, H., Ma, H., & Zhang, X. (2023) · Sensors · doi:10.3390/s23094399 · Cited by 24
“[25] combined LSTM and autoencoder to extract the timing features in the network traffic of the IoV, which improved the accuracy of intrusion detection in the IoV.”
MethodCao, J., Di, X., Liu, X., Li, J., Li, Z., Zhao, L., Hawbani, A., & Guizani, M. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3351438 · Cited by 23
“Despite improving the driving experience with Vehicle-to-Everything (V2X) technologies, the attacked surface of the In-Vehicle Network (IVN) in ICVs is increasing, resulting in IVN being more prone to anomalies and even imperiling the life safety of drivers [3], [4], [5], [6].”
BackgroundYangyang, L. I. U., Xue, L., Wang, S., Luo, X., Zhao, K., Jing, P., Ma, X., Tang, Y., & Zhou, H. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3567940 · Cited by 28
“Ashraf et al. [184] employed a combination of LSTM and autoen-coder to extract timing features from Internet of Vehicles network traffic, enhancing the accuracy of intrusion detection in the Internet of Vehicles.”
Shahi, S., Fenton, F. H., & Cherry, E. M. (2022) · Chaos An Interdisciplinary Journal of Nonlinear Science · doi:10.1063/5.0087812 · Cited by 22
An Intelligent Risk Management Framework for Monitoring Vehicular Engine Health
Rahim, M. A., Rahman, M. A., Rahman, M. M., Zaman, N., Moustafa, N., & Razzak, I. (2022) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2022.3179350 · Cited by 22
“For this reason, AI has received much attention in recent years for its success in monitoring mechanical items health utilising various sensors and viable algorithms like machine learning (ML), deep learning (DL), and so on [3].”
BackgroundMethodInfluentialSelf-citationIDS-DEC: A novel intrusion detection for CAN bus traffic based on deep embedded clustering
Shi, J., Xie, Z., Dong, L., Jiang, X., & Jin, X. (2024) · Vehicular Communications · doi:10.1016/j.vehcom.2024.100830 · Cited by 22
Mouti, S., Shukla, S. K., Althubiti, S. A., Ahmed, M. A., Alenezi, F. S., & Arumugam, M. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108308 · Cited by 21
Yanmin, C., Sarkar, A., Zain, J. M., Bhar, A., Noorwali, A., & Othman, K. M. (2024) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-024-02401-2 · Cited by 25
“For ITS (Intelligent Transportation Systems), Ashraf et al. [11] recommended a DL-based IDS that learns how intra-vehicle networks regular network traffic behaves, V2I networks and V2V communications.”
Intelligence-Based Strategies with Vehicle-to-Everything Network: A Review
Bohra, N., Kumari, A., Mishra, V. K., Soni, P. K., & Balyan, V. (2025) · Future Internet · doi:10.3390/fi17020079 · Cited by 28
CNN-CLFFA: Support Mobile Edge Computing in Transportation Cyber Physical System
Bhansali, A., Patra, R. K., Divakarachari, P. B., Falkowski‐Gilski, P., Shivakanth, G., & Patil, S. N. (2024) · IEEE Access · doi:10.1109/access.2024.3361837 · Cited by 20
“In the ITS, Ashraf et al. [17] have presented an effective Intrusion Detection System (IDS) for finding the suspicious activities in vehicles to infrastructure networks, in-vehicles networks, and vehicles to vehicles communications.”
BackgroundChen, R., Chen, X., & Zhao, J. (2024) · Computer Networks · doi:10.1016/j.comnet.2024.110560 · Cited by 24
Yagiz, M. A., MohajerAnsari, P., Pesé, M. D., & Göktaş, P. (2024) · ACM Workshop on CPS&IoT Security and Privacy (CPSIoTSec) · doi:10.1145/3690134.3694819 · Cited by 20
“Ashraf et al. [2] utilized DL for intrusion detection in transportation systems, employing a LSTM autoencoder to identify malicious network behaviors in IVNs and vehicle-to-infrastructure networks.”
The role of machine and deep learning in modern intrusion detection systems: A comprehensive review
Akuthota, U. C., & Bhargava, L. (2025) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2025.110318 · Cited by 24
Huan, S., Zhang, X., Shang, W., Cao, H., Li, H., Yang, Y., & Liu, W. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3478371 · Cited by 18
“This method normalizes the likelihood of features to obtain thresholds for discrimination, which greatly improves the versatility of detection [35].”
SecureBERT and Llama 2 Empowered Control Area Network Intrusion Detection and Classification
Li, X., & Fu, H. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3596915 · Cited by 18
“In particular, our work has unique innovations which yield significant results, including: [14], [15], [16], [17], [18], [19], [20], [21]) require a larger dataset to achieve a performance level similar to ours.”
Chen, R., Chen, X., & Zhao, J. (2024) · PLoS ONE · doi:10.1371/journal.pone.0301897 · Cited by 22
Rousta, M. M., Arani, P. F., Kazemi, R., & Shoorehdeli, M. A. (2024) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.12359 · Cited by 17
Metadata
- Authors
- Ashraf, J., Bakhshi, A. D., Moustafa, N., Khurshid, H., Javed, A., & Beheshti, A.
- Affiliations
- National University of Sciences and Technology (PK)
- UNSW Sydney (AU)
- Sir Syed CASE Institute of Technology (PK)
- Macquarie University (AU)
- Venue
- IEEE Transactions on Intelligent Transportation Systems
- Published
- 2021-07
- Volume
- 22
- Issue
- 7
- Pages
- 4507-4518
- ISSN
- 1524-9050 (ISSN-L)
- 1558-0016
- OpenAlex
- W3136873430
- Semantic Scholar
- 49aca6415518fce1b25e48d852c53e838b3cba76
- Cited by
- 295
- References
- 42
- Citations by year
- 2026: 35 · 2025: 70 · 2024: 69 · 2023: 57 · 2022: 45 · 2021: 19
- FWCI
- 14.22
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Intelligent Transportation Systems (publishedVersion)
- Funders
- 2020 Australian Spitfire Memorial Defence Fund (PS39150)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Vehicular Ad Hoc Networks (VANETs)
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- intrusion detection, intelligent transportation systems, autonomous vehicles, Internet of Vehicles, in-vehicle networks, LSTM autoencoder, anomaly detection, cyberattacks, vehicle-to-vehicle communication, vehicle-to-infrastructure communication, car hacking, network 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.