GIDS: GAN based Intrusion Detection System for In-Vehicle Network

Seo, Eunbi; Song, Hyun Min; Kim, Huy Kang

doi:10.1109/pst.2018.8514157

Cited by 355 publications

(263 citation statements)

References 9 publications

Supporting

Mentioning

262

Contrasting

Order By: Relevance

“…To overcome these challenges, there should be more research on modelling CAN bus attacks like in [80] and creating attack databases like in [81,82]. Sharing datasets as an open-source (e.g., like in [66]) will help researchers; hence working on shared datasets will give a reference point to compare their research.…”

Section: Discussion On Can Security Researchmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of CAN Bus Security Challenges

Bozdal

Samie

Aslam

et al. 2020

Sensors

125

View full text Add to dashboard Cite

The automobile industry no longer relies on pure mechanical systems; instead, it benefits from many smart features based on advanced embedded electronics. Although the rise in electronics and connectivity has improved comfort, functionality, and safe driving, it has also created new attack surfaces to penetrate the in-vehicle communication network, which was initially designed as a close loop system. For such applications, the Controller Area Network (CAN) is the most-widely used communication protocol, which still suffers from various security issues because of the lack of encryption and authentication. As a result, any malicious/hijacked node can cause catastrophic accidents and financial loss. This paper analyses the CAN bus comprehensively to provide an outlook on security concerns. It also presents the security vulnerabilities of the CAN and a state-of-the-art attack surface with cases of implemented attack scenarios and goes through different solutions that assist in attack prevention, mainly based on an intrusion detection system (IDS).

show abstract

Section: Discussion On Can Security Researchmentioning

confidence: 99%

“…Generative adversarial nets (GAN) based IDS [66] was proposed by Seo et al, who used the deep-learning model. The method is easy to expand and difficult to manipulate by an attacker, hence the detection mechanism has a black-box characteristic.…”

Section: Feature-based Idsmentioning

confidence: 99%

Evaluation of CAN Bus Security Challenges

Bozdal

Samie

Aslam

et al. 2020

Sensors

125

View full text Add to dashboard Cite

show abstract

“…To evaluate the proposed IDS, this work considers two different datasets for the purpose of its implementation in both intra-vehicle and external networks as described in Section III-A. The first data set is called "Car-Hacking Dataset" or "CAN-intrusion dataset" which was proposed in 2018 for the purpose of IDS development on CAN bus [6]. On the other hand, to build a comprehensive IDS that can also be effective in external communication networks, a standard IDS data set containing the most updated attack scenarios, named "CICIDS2017" [5], is considered in this work.…”

Section: A Datasets Descriptionmentioning

confidence: 99%

Tree-Based Intelligent Intrusion Detection System in Internet of Vehicles

Yang

Moubayed

Hamieh

et al. 2019

2019 IEEE Global Communications Conference (GLOBECOM)

167

View full text Add to dashboard Cite

The use of autonomous vehicles (AVs) is a promising technology in Intelligent Transportation Systems (ITSs) to improve safety and driving efficiency. Vehicle-to-everything (V2X) technology enables communication among vehicles and other infrastructures. However, AVs and Internet of Vehicles (IoV) are vulnerable to different types of cyber-attacks such as denial of service, spoofing, and sniffing attacks. In this paper, an intelligent intrusion detection system (IDS) is proposed based on tree-structure machine learning models. The results from the implementation of the proposed intrusion detection system on standard data sets indicate that the system has the ability to identify various cyber-attacks in the AV networks. Furthermore, the proposed ensemble learning and feature selection approaches enable the proposed system to achieve high detection rate and low computational cost simultaneously.

show abstract

“…One significant advantage of this approach is that attacks are effectively detected without changing the existing in-vehicle network structure. Seo et al [16] proposed a double discriminator using the generative adversarial networks (GAN). The method uses two different data sets to train two discriminators, which greatly improves the detection accuracy of IDS.…”

Section: Related Workmentioning

confidence: 99%

“…An extremely important problem is that the computational cost of machine-learning-based IDSs is considerably high. In contrast, we propose an IDS for in-vehicle network that can address these problems and the required computation shows advantage over preceding methods [16,17]. Table 2.…”

Section: Related Workmentioning

confidence: 99%

Internet of Things Meets Vehicles: Sheltering In-Vehicle Network through Lightweight Machine Learning

Xiao

2019

Symmetry

View full text Add to dashboard Cite

An internet of vehicles allows intelligent automobiles to interchange messages with other cars, traffic management departments, and data analysis companies about vehicle identification, accident detection, and danger warnings. The implementation of these features requires Internet of Things system support. Smart cars are generally equipped with many (hundreds or even thousands of) sensors and microcomputers so that drivers gain more information about travel. The connection between the in-vehicle network and the Internet can be leveraged by the attackers in a malicious manner and thus increases the number of ways the in-vehicle network can now be targeted. Protecting increasingly intelligent vehicle systems becomes more difficult, especially because a network of many different devices makes the system more vulnerable than ever before. The paper assumes a generic threat model in which attackers can access the controller area network (CAN) bus via common access points (e.g., Bluetooth, OBD-II, Wi-Fi, physical access, and cellular communication, etc). A machine learning based simplified attention (SIMATT)-security control unit (SECCU) symmetry framework is proposed towards a novel and lightweight anomaly detecting mechanism for the in-vehicle network. For this framework, we propose two new models, SECCU and SIMATT, and obtain state-of-the-art anomaly detecting performance when fusing the former to the latter. Regardless of the training phase or the detection phase, we strive to minimize the computational cost and thereby obtain a lightweight anomaly detection method. In particular, the SECCU model has only one layer of 500 computing cells and the SIMATT model has been improved to reduce its computational costs. Through substantial experiment comparisons (with various classical algorithms, such as LSTM, GRU, GIDS, RNN, or their variations), it is demonstrated that the SIMATT-SECCU framework achieves an almost optimal accuracy and recall rate.

show abstract

GIDS: GAN based Intrusion Detection System for In-Vehicle Network

Cited by 355 publications

References 9 publications

Evaluation of CAN Bus Security Challenges

Evaluation of CAN Bus Security Challenges

Tree-Based Intelligent Intrusion Detection System in Internet of Vehicles

Internet of Things Meets Vehicles: Sheltering In-Vehicle Network through Lightweight Machine Learning

Contact Info

Product

Resources

About