An adversarial approach for intrusion detection systems using Jacobian Saliency Map Attacks (JSMA) Algorithm
- Submitting institution
-
Glasgow Caledonian University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 42310358
- Type
- D - Journal article
- DOI
-
10.3390/computers9030058
- Title of journal
- Computers
- Article number
- 58
- First page
- -
- Volume
- 9
- Issue
- 3
- ISSN
- 2073-431X
- Open access status
- Compliant
- Month of publication
- July
- Year of publication
- 2020
- 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
-
4
- Research group(s)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- AI and Machine learning is being used more recently in intrusion detection by hackers and government agencies. Machine learning intrusion detection has many challenges in defending against these adversarial attacks. The novel random neural network-based adversarial intrusion detection system proposed in this paper is one of the best performing methods in only a handful of methods that are available against these attacks, and gives very good general protection against multiple smart intrusion attacks. This research is underpinned by a new awarded KTP project with Stream Technologies Ltd. (Real-time Security monitoring of IoT using Deep learning and Random Neural Networks).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -