Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A Multitask Learning Approach for Intrusion Detection in Controller Area Networks.

Bianca Brişan1, Camil Jichici1, Raul Robu1

  • 1Faculty of Automatics and Computers, Politehnica University of Timisoara, 300223 Timişoara, Timiş, Romania.

Sensors (Basel, Switzerland)
|June 12, 2026
PubMed
Summary

This study introduces a novel intrusion detection system for in-vehicle networks, combining sliding windows and multitask learning for enhanced accuracy and efficiency. This approach effectively handles diverse and coexisting cyberattacks, improving real-world security.

Related Concept Videos

Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
Control Systems: Applications01:25

Control Systems: Applications

Electrical engineering plays a pivotal role in our daily lives, with control systems at the heart of many applications, from home appliances to sophisticated space shuttles. Control systems manage and regulate the behavior of devices and processes, ensuring they function safely, correctly, and efficiently.
In modern vehicles, control systems manage various functions to enhance performance and safety. The steering wheel and accelerator are primary inputs in a car's control system. The direction...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

AudioUnlock: Device-to-Device Authentication via Acoustic Signatures and One-Class Classifiers.

Sensors (Basel, Switzerland)·2025
Same author

Smartphone Camera Identification from Low-Mid Frequency DCT Coefficients of Dark Images.

Entropy (Basel, Switzerland)·2022
Same author

From data mining rules to medical logical modules and medical advices.

Studies in health technology and informatics·2013
Same author

Regional medical data mining system.

Studies in health technology and informatics·2011

Area of Science:

  • Cybersecurity
  • Automotive Engineering
  • Machine Learning

Background:

  • Intrusion detection systems (IDS) for in-vehicle networks demand high accuracy and computational efficiency for real-world application.
  • Increasingly diverse cyberattacks pose challenges to achieving both accuracy and efficiency simultaneously.
  • Existing methods often struggle with the complexity of multiple, concurrent attack types within network traffic.

Purpose of the Study:

  • To develop and evaluate an intrusion detection approach that optimizes both accuracy and computational efficiency for in-vehicle networks.
  • To investigate the combined benefits of sliding window batch processing and multitask learning for enhanced intrusion detection.
  • To address the challenge of detecting coexisting attack types within network data streams.

Main Methods:

Keywords:
CAN busintrusion detectionmultitask learning

Related Experiment Videos

  • Utilized sliding windows for efficient batch processing of network frames, reducing computational load.
  • Implemented multitask learning to share common features across different attack classes, improving detection generalization.
  • Developed a new, more complex attack dataset to rigorously test the proposed method.
  • Analyzed feature-level similarities between attack and legitimate frames using mutual information.

Main Results:

  • Demonstrated significant computational savings through the use of sliding windows.
  • Showcased the necessity and benefits of multitask learning in accurately identifying multiple, coexisting attack types.
  • Validated the approach on three existing datasets and a newly created complex dataset, confirming improved detection rates and efficiency.

Conclusions:

  • The combination of sliding windows and multitask learning offers a robust solution for accurate and computationally efficient intrusion detection in automotive networks.
  • Multitask learning is crucial for handling scenarios where multiple attack types occur within the same processing window.
  • The proposed method provides a practical advancement for securing in-vehicle communication systems against sophisticated cyber threats.