A Novel Intrusion Detection Method Using Deep Neural Network for In-Vehicle Network Security

Kang, Minju; Kang, Je-Won

doi:10.1109/vtcspring.2016.7504089

Cited by 152 publications

(53 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To assess the effectiveness of the proposed detection algorithm we simulated attacker activities by injecting forged CAN messages within traffic traces gathered from an unmodified licensed vehicle. This process has already been adopted for the evaluation of several intrusion detection algorithms based on the CAN bus [1], [5], and allows us to simulate the effects over the CAN bus of real attack strategies [2], [6], [3].…”

Section: Attack Scenariosmentioning

confidence: 99%

“…Besides detection performance, it is also imperative to design detection algorithms that are compatible with the tight computational constraints of automotive ECUs. As an example, while the work proposed in [5] represents an interesting detection approach based on Deep Neural Network, its high computational cost render it clearly unsuitable for modern vehicles.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Anomaly detection of CAN bus messages through analysis of ID sequences

Marchetti

Stabili

2017

2017 IEEE Intelligent Vehicles Symposium (IV)

182

View full text Add to dashboard Cite

This paper proposes a novel intrusion detection algorithm that aims to identify malicious CAN messages injected by attackers in the CAN bus of modern vehicles. The proposed algorithm identifies anomalies in the sequence of messages that flow in the CAN bus and is characterized by small memory and computational footprints, that make it applicable to current ECUs. Its detection performance are demonstrated through experiments carried out on real CAN traffic gathered from an unmodified licensed vehicle

show abstract

Section: Attack Scenariosmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Anomaly detection of CAN bus messages through analysis of ID sequences

Marchetti

Stabili

2017

2017 IEEE Intelligent Vehicles Symposium (IV)

182

View full text Add to dashboard Cite

show abstract

“…Another big concern is the privacy on individual user data [97,98] . In the IoV, each vehicle has its own personal data and may not want to share with other vehicles, roadside units, or the central platforms.…”

Section: Security and Privacymentioning

confidence: 99%

Wireless recommendations for Internet of vehicles: Recent advances, challenges, and opportunities

Luo

et al. 2020

Intell. and Converged Netw.

View full text Add to dashboard Cite

Internet of Vehicles (IoV) is a distributed network of connected cars, roadside infrastructure, wireless communication networks, and central cloud platforms. Wireless recommendations play an important role in the IoV network, for example, recommending appropriate routes, recommending driving strategies, and recommending content. In this paper, we review some of the key techniques in recommendations and discuss what are the opportunities and challenges to deploy these wireless recommendations in the IoV.

show abstract

“…In their experiments, it was able to detect irregular changes in CAN bus messages with a false positive rate that did not exceed 2.5%, but it has not been evaluated against specific attacks. In contrast to almost all other IDSs designed for CAN, which opt for very lightweight behaviour-based approaches, Kang et al [79] have proposed the use of a Deep Neural Network in a knowledge-based fashion. Their neural network is trained on high-dimensional CAN frame data to figure out the underlying statistical properties of normal and attack CAN frames and extract the corresponding features.…”

Section: Accepted Manuscriptmentioning

confidence: 99%

A taxonomy and survey of cyber-physical intrusion detection approaches for vehicles

Karapistoli²,

et al. 2019

View full text Add to dashboard Cite

With the growing threat of cyber and cyber-physical attacks against automobiles, drones, ships, driverless pods and other vehicles, there is also a growing need for intrusion detection approaches that can facilitate defence against such threats. Vehicles tend to have limited processing resources and are energy-constrained. So, any security provision needs to abide by these limitations. At the same time, attacks against vehicles are very rare, often making knowledge-based intrusion detection systems less practical than behaviour-based ones, which is the reverse of what is seen in conventional computing systems. Furthermore, vehicle design and implementation can differ wildly between different types or different manufacturers, which can lead to intrusion detection designs that are vehicle-specific. Equally importantly, vehicles are practically defined by their ability to move, autonomously or not. Movement, as well as other physical manifestations of their operation may allow cyber security breaches to lead to physical damage, but can also be an opportunity for detection. For example, physical sensing can contribute to more accurate or more rapid intrusion detection through observation and analysis of physical manifestations of a security breach. This paper presents a classification and survey of intrusion detection systems designed and evaluated specifically on vehicles and networks of vehicles. Its aim is to help identify existing techniques that can be adopted in the industry, along with their advantages and disadvantages, as well as to identify gaps in the literature, which are attractive and highly meaningful areas of future research.

show abstract

A Novel Intrusion Detection Method Using Deep Neural Network for In-Vehicle Network Security

Cited by 152 publications

References 7 publications

Anomaly detection of CAN bus messages through analysis of ID sequences

Anomaly detection of CAN bus messages through analysis of ID sequences

Wireless recommendations for Internet of vehicles: Recent advances, challenges, and opportunities

A taxonomy and survey of cyber-physical intrusion detection approaches for vehicles

Contact Info

Product

Resources

About