Cloud-based cyber-physical intrusion detection for vehicles using Deep Learning
- Submitting institution
-
University of Greenwich
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 18213
- Type
- D - Journal article
- DOI
-
10.1109/ACCESS.2017.2782159
- Title of journal
- IEEE Access
- Article number
- -
- First page
- 3491
- Volume
- 6
- Issue
- UNSPECIFIED
- ISSN
- 2169-3536
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
5
- Research group(s)
-
-
- Citation count
- 39
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work tackles the challenge of applying an advanced intrusion detection technique based on deep learning to a robotic vehicle that does not have the processing power to run it in a timely manner onboard. It does so by applying the concept of computation offloading previously used in mobile computing, but adapted to account for the time criticality of the domain. For this, it produced a further innovation, which was a mathematical model that can help determine in which scenarios it is practical to offload an intrusion detection task to the cloud depending on the current condition of the network.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
