EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Multitask Learning Approach for Intrusion Detection in Controller Area Networks

Bianca Brişan, Camil Jichici iD, Raul Robu, Bogdan Groza iD

Sensors · 29.05.2026 · 26 (11) · 3432

DOI: 10.3390/s26113432 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 29.05.2026. Verfasst von Bianca Brişan und 3 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Automatics and Computers, Politehnica University of Timisoara, 300223 Timişoara, Timiş, Romania. Die Arbeit nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: CNCS - UEFISCDI, Ministry of Research, Innovation and Digitization, CNCS-UEFISCDI.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Intrusion detection on in-vehicle networks requires high accuracy, which is reported by many papers so far, but also computational efficiency to make it suitable for real-world scenarios. The achievement of both requirements at the same time becomes harder to achieve, especially as the number of attacks diversifies. An approach to leverage computational costs is the use of sliding windows, i.e., batch processing, which extends the detection over multiple frames, but the use of multitask learning is also advantageous because a number of layers are shared between classes to extract common relevant features. While indeed the greatest computational gains are from the use of a sliding window, multitask learning has benefits too and is in fact necessary as multiple attack types can coexist in the same window. We explore the benefits of this approach on three existing attack datasets and we also build our own dataset that garners more attack complexity so that we can concretely measure the benefits of multitask learning both in terms of detection rate and computational savings. Our approach considers the feature-level similarity between attack types and legitimate frames, extracted from the mutual information between the two, and extends detection over windows of multiple frames, which justify multitask learning as frames belonging to different classes can co-exist in the same window.

Schlagwörter

Stichwörter der Autor:innen

CAN busintrusion detectionmultitask learning

Autor:innen und Institutionen

  • Faculty of Automatics and Computers, Politehnica University of Timisoara, 300223 Timişoara, Timiş, Romania.

ORCID-Profile: Camil Jichici, Bogdan Groza

Förderung

  • CNCS - UEFISCDI
  • Ministry of Research, Innovation and Digitization, CNCS-UEFISCDI

Zitieren

APA

Brişan, B., Jichici, C., Robu, R., & Groza, B. (2026). A Multitask Learning Approach for Intrusion Detection in Controller Area Networks. Sensors, 26(11), 3432. https://doi.org/10.3390/s26113432

Vancouver

Brişan B, Jichici C, Robu R, Groza B. A Multitask Learning Approach for Intrusion Detection in Controller Area Networks. Sensors. 2026;26(11):3432. doi:10.3390/s26113432

BibTeX
@article{Brian2026,
  author = {Brişan, Bianca and Jichici, Camil and Robu, Raul and Groza, Bogdan},
  title = {A Multitask Learning Approach for Intrusion Detection in Controller Area Networks},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {11},
  pages = {3432},
  doi = {10.3390/s26113432}
}
Kostenlos starten →