Hybrid Deep Learning for Botnet Attack Detection in the Internet of Things Networks
- Submitting institution
-
Manchester Metropolitan University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2397
- Type
- D - Journal article
- DOI
-
10.1109/JIOT.2020.3034156
- Title of journal
- IEEE Internet of Things Journal
- Article number
- 9241019
- First page
- 4944
- Volume
- 8
- Issue
- 6
- ISSN
- 2327-4662
- Open access status
- Not compliant
- Month of publication
- October
- Year of publication
- 2020
- URL
-
https://e-space.mmu.ac.uk/627198/
- 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
-
4
- Research group(s)
-
D - Smart Infrastructure
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- An international collaborative effort with contributions to feature dimensionality reduction for large-scale Internet of Things (IoT) network data and botnet detection. Comprehensive experimental evaluation showed that the proposed methods reduce memory space requirements by up to 91.8% compared to state-of-the-art methods. This research has been commercialised by Cyraatek (Akin@cyraatek.com) as part of their cloud-based IoT auditing and intrusion detection platform. Additionally, this work led to a new collaboration with Blueskytec (nigel.mackie@blueskytec.com) and funding from Innovate UK to secure cypher-physical systems on naval ships (KTP94125).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -