Transfer learning-based self-learning intrusion detection system for in-vehicle networks.
Saved in:
| Title: | Transfer learning-based self-learning intrusion detection system for in-vehicle networks. |
|---|---|
| Authors: | Wang, Yuhang1 (AUTHOR), Lai, Yingxu1,2 (AUTHOR) laiyingxu@bjut.edu.cn, Chen, Ye1 (AUTHOR), Wei, Jingwen1 (AUTHOR), Zhang, Zhaoyi1 (AUTHOR) |
| Source: | Neural Computing & Applications. May2023, Vol. 35 Issue 14, p10257-10273. 17p. |
| Subjects: | Intrusion detection systems (Computer security), In-vehicle computing, Electronic control, Data transmission systems, Telecommunication, Problem solving, Cyberterrorism |
| Abstract: | Controller area networks (CANs) are the de-facto standard for in-vehicle networks and enable real-time data communication between the electronic control units in a vehicle. However, owing to inadequate security mechanisms, CANs are vulnerable to cyberattacks. The sophistication of these attacks evolves constantly and new types of attacks emerge over time. Most existing intrusion detection systems (IDSs) can handle known attacks, but their ability to detect unknown attacks requires urgent improvements. Although IDSs can be updated via the Internet of Vehicles cloud to improve their detection performance, an unacceptable amount of time is required to collect enough labeled data and the updates are slow. Considering these problems, we propose a transfer learning-based self-learning IDS (TLSIDS) for CANs. The proposed TLSIDS uses a cascade detection approach that is capable of detecting both known and unknown attacks with high performance, and the self-learning function can solve the problem of slow updates, thus improving the speed and performance of the TLSIDS in detecting unknown attacks. The TLSIDS consists of four modules, namely the basic detection module (BDM), the advanced detection module (ADM), the unknown attacks classification module (UACM), and the self-learning module (SLM). The efficacy of the TLSIDS was evaluated using a public dataset provided by the Hacking and Countermeasure Research Lab (HCRL). The results revealed that our proposed TLSIDS has effectiveness and robustness in distinct scenarios. [ABSTRACT FROM AUTHOR] |
| Copyright of Neural Computing & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 163294434 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Transfer learning-based self-learning intrusion detection system for in-vehicle networks. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Wang%2C+Yuhang%22">Wang, Yuhang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lai%2C+Yingxu%22">Lai, Yingxu</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> laiyingxu@bjut.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Chen%2C+Ye%22">Chen, Ye</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wei%2C+Jingwen%22">Wei, Jingwen</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Zhaoyi%22">Zhang, Zhaoyi</searchLink><relatesTo>1</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Neural+Computing+%26+Applications%22">Neural Computing & Applications</searchLink>. May2023, Vol. 35 Issue 14, p10257-10273. 17p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Intrusion+detection+systems+%28Computer+security%29%22">Intrusion detection systems (Computer security)</searchLink><br /><searchLink fieldCode="DE" term="%22In-vehicle+computing%22">In-vehicle computing</searchLink><br /><searchLink fieldCode="DE" term="%22Electronic+control%22">Electronic control</searchLink><br /><searchLink fieldCode="DE" term="%22Data+transmission+systems%22">Data transmission systems</searchLink><br /><searchLink fieldCode="DE" term="%22Telecommunication%22">Telecommunication</searchLink><br /><searchLink fieldCode="DE" term="%22Problem+solving%22">Problem solving</searchLink><br /><searchLink fieldCode="DE" term="%22Cyberterrorism%22">Cyberterrorism</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Controller area networks (CANs) are the de-facto standard for in-vehicle networks and enable real-time data communication between the electronic control units in a vehicle. However, owing to inadequate security mechanisms, CANs are vulnerable to cyberattacks. The sophistication of these attacks evolves constantly and new types of attacks emerge over time. Most existing intrusion detection systems (IDSs) can handle known attacks, but their ability to detect unknown attacks requires urgent improvements. Although IDSs can be updated via the Internet of Vehicles cloud to improve their detection performance, an unacceptable amount of time is required to collect enough labeled data and the updates are slow. Considering these problems, we propose a transfer learning-based self-learning IDS (TLSIDS) for CANs. The proposed TLSIDS uses a cascade detection approach that is capable of detecting both known and unknown attacks with high performance, and the self-learning function can solve the problem of slow updates, thus improving the speed and performance of the TLSIDS in detecting unknown attacks. The TLSIDS consists of four modules, namely the basic detection module (BDM), the advanced detection module (ADM), the unknown attacks classification module (UACM), and the self-learning module (SLM). The efficacy of the TLSIDS was evaluated using a public dataset provided by the Hacking and Countermeasure Research Lab (HCRL). The results revealed that our proposed TLSIDS has effectiveness and robustness in distinct scenarios. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Neural Computing & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=163294434 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s00521-023-08233-5 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 17 StartPage: 10257 Subjects: – SubjectFull: Intrusion detection systems (Computer security) Type: general – SubjectFull: In-vehicle computing Type: general – SubjectFull: Electronic control Type: general – SubjectFull: Data transmission systems Type: general – SubjectFull: Telecommunication Type: general – SubjectFull: Problem solving Type: general – SubjectFull: Cyberterrorism Type: general Titles: – TitleFull: Transfer learning-based self-learning intrusion detection system for in-vehicle networks. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Wang, Yuhang – PersonEntity: Name: NameFull: Lai, Yingxu – PersonEntity: Name: NameFull: Chen, Ye – PersonEntity: Name: NameFull: Wei, Jingwen – PersonEntity: Name: NameFull: Zhang, Zhaoyi IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 05 Text: May2023 Type: published Y: 2023 Identifiers: – Type: issn-print Value: 09410643 Numbering: – Type: volume Value: 35 – Type: issue Value: 14 Titles: – TitleFull: Neural Computing & Applications Type: main |
| ResultId | 1 |
