Novel Deep Learning-Enabled LSTM Autoencoder Architecture for Discovering Anomalous Events From Intelligent Transportation Systems

Ashraf, Javed; Bakhshi, Asim Dilawer; Moustafa, Nour; Khurshid, Hasnat; Javed, Abdullah; Beheshti, Amin

doi:10.1109/tits.2020.3017882

Cited by 150 publications

(67 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On training B, if the detection of unknown attacks is not included, the method can reach 96.26%, 99.07%, and 96.70% in accuracy, precision, and recall, respectively. Compared with the method using the same data sets [ 55 , 56 ], the method in this paper has a better performance in detection accuracy. Even compared with other advanced methods that use a large number of samples for training [ 43 , 53 ], the overall performance of this method is still not behind.…”

Section: Methodsmentioning

confidence: 99%

A Few‐Shot Learning‐Based Siamese Capsule Network for Intrusion Detection with Imbalanced Training Data

Wang

Tian

Qin

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Network intrusion detection remains one of the major challenges in cybersecurity. In recent years, many machine-learning-based methods have been designed to capture the dynamic and complex intrusion patterns to improve the performance of intrusion detection systems. However, two issues, including imbalanced training data and new unknown attacks, still hinder the development of a reliable network intrusion detection system. In this paper, we propose a novel few-shot learning-based Siamese capsule network to tackle the scarcity of abnormal network traffic training data and enhance the detection of unknown attacks. In specific, the well-designed deep learning network excels at capturing dynamic relationships across traffic features. In addition, an unsupervised subtype sampling scheme is seamlessly integrated with the Siamese network to improve the detection of network intrusion attacks under the circumstance of imbalanced training data. Experimental results have demonstrated that the metric learning framework is more suitable to extract subtle and distinctive features to identify both known and unknown attacks after the sampling scheme compared to other supervised learning methods. Compared to the state-of-the-art methods, our proposed method achieves superior performance to effectively detect both types of attacks.

show abstract

Section: Methodsmentioning

confidence: 99%

A Few‐Shot Learning‐Based Siamese Capsule Network for Intrusion Detection with Imbalanced Training Data

Wang

Tian

Qin

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…The authors of [37] propose a deep learning-based IDS to detect cyber-attacks in CANs. It relies on long shortterm memory (LSTM) autoencoders and achieves 99% accuracy at detecting attacks.…”

Section: Related Workmentioning

confidence: 99%

“…Although the CAN protocol is considered a legacy technology and there are other network protocols that offer higher throughput, such as media oriented systems transport (MOST) and automotive Ethernet, it is still the most used protocol in today's cars [26], [37], [39]. Its robustness and low complexity allow car manufacturers to still rely on it for many modern applications, so CANs are expected to continue being widely used in vehicles.…”

Section: A Controller Area Networkmentioning

confidence: 99%

An Efficient Intrusion Prevention System for CAN: Hindering Cyber-Attacks With a Low-Cost Platform

Araujo-Filho¹,

Pinheiro

Kaddoum

et al. 2021

IEEE Access

View full text Add to dashboard Cite

The controller area network (CAN), which is still today the most used in-vehicle network, does not provide any security or authentication mechanism by design. Since current vehicles, which have numerous connectivity technologies, such as Bluetooth, Wi-Fi, and cellular radio, can be easily accessed from the exterior world, they can be easy targets of cyber-attacks. It is therefore urgently necessary to enhance vehicle security by detecting and stopping cyber-attacks. In this paper, we propose a novel unsupervised intrusion prevention system (IPS) for automotive CANs that detects and hinders attacks without modifying the architecture of the electronic control units (ECUs) or requiring information that is restricted to car manufacturers. We compare two machine learning algorithms' ability to detect fuzzing and spoofing attacks, and evaluate which of them is most accurate with the fewest number of data bytes. The fewer data bytes required, the sooner detection can start and the sooner attacking frames can be detected. Experiment results show that our proposed detection mechanism achieves accuracy higher than 99%, F1-scores higher than 97%, and detection times shorter than 80µs for the types of attacks considered. Moreover, when compared to four state-of-the-art intrusion detection systems, it is the only solution that is capable of discarding attacking frames before damage occurs while being deployed on inexpensive Raspberry Pi. Such an inexpensive deployment is particularly desirable, as cost is one of the automotive industry's primary concerns. INDEX TERMS IntrusionDetection System (IDS), Intrusion Prevention System (IPS), Machine Learning, Controller Area Network (CAN).

show abstract

“…The results of MABAC started with the opinion of three experts in a comparison matrix with the scale of SVNNs; after that, this scale is converted to a crisp value and three comparison matrices are aggregated in one matrix using Eqs. (1)(2)(3)(4). The comparison matrix between the criteria and alternatives is listed in Table IV.…”

Section: Applicationmentioning

confidence: 99%

“…Autonomous vehicles are one of the major categories of ITS that could result in reducing the requirements of drivers, decreasing transportation expenditures, and improving traffic flows. Those vehicles can be connected with other ones, where they are connected using communication techniques and tools which are known as vehicles to everything (V2X) [1]. V2X can be represented in various technological forms, including vehicle-to-infrastructure (V2I), vehicle-to-vehicle (V2V), vehicle-to-pedestrian (V2P and vehicle-to-network (V2N) systems.…”

Section: Introductionmentioning

confidence: 99%

A Security-by-Design Decision-Making Model for Risk Management in Autonomous Vehicles

et al. 2021

Self Cite

View full text Add to dashboard Cite

Autonomous/self-driving vehicles have gained significant attention these days, as one of the intelligent transportation systems. However, those vehicles have risks related to their physical implementation and security against cyber threats. Therefore, this study proposes a new security-by-design model for estimating the uncertainty of autonomous vehicles and measuring cyber risks; thus it assists decision-makers in addressing the risks of the physical design and their attack surfaces. The proposed model is developed using neutrosophic sets that efficiently tackle multi-criteria decision-making (MCDM) problems with extensive conflicting criteria and alternatives. The proposed model integrates MCDM, Analytic Hierarchy Process (AHP), Multi-Attributive Border Approximation Area Comparison (MABAC), and Preference Ranking Organization Method for Enrichment Evaluations II (PROMETHEE II), along with single-valued neutrosophic sets (SVNSs). An illustrative case considering ten risks in self-driving vehicles is used to validate the feasibility of the proposed model. Compared to the state-of-the-art methods, the proposed model is considered consistent and reliable to deal with and represent uncertainty and incomplete risk information using neutrosophic sets.

show abstract

Novel Deep Learning-Enabled LSTM Autoencoder Architecture for Discovering Anomalous Events From Intelligent Transportation Systems

Cited by 150 publications

References 38 publications

A Few‐Shot Learning‐Based Siamese Capsule Network for Intrusion Detection with Imbalanced Training Data

A Few‐Shot Learning‐Based Siamese Capsule Network for Intrusion Detection with Imbalanced Training Data

An Efficient Intrusion Prevention System for CAN: Hindering Cyber-Attacks With a Low-Cost Platform

A Security-by-Design Decision-Making Model for Risk Management in Autonomous Vehicles

Contact Info

Product

Resources

About