Improving SIEM for critical SCADA water infrastructures using machine learning
- Submitting institution
-
Abertay University
- Unit of assessment
- 12 - Engineering
- Output identifier
- 17661857
- Type
- E - Conference contribution
- DOI
-
10.1007/978-3-030-12786-2_1
- Title of conference / published proceedings
- Computer security : ESORICS 2018 International Workshops, CyberICPS 2018 and SECPRE 2018, Barcelona, Spain, September 6–7, 2018, revised selected papers
- First page
- 3
- Volume
- 11387
- Issue
- -
- ISSN
- 0302-9743
- Open access status
- Compliant
- Month of publication
- January
- Year of publication
- 2019
- 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)
-
C - Cybersecurity
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Evaluates machine learning (ML) algorithms’ performance at detecting anomalies – including hardware failures, sabotage, and cyber-attacks – against a testbed that simulates water distribution and storage. The system created for the experiment resembles many complex industrial SCADA systems. Interest in the work has been logged via (https://github.com/AbertayMachineLearningGroup/machine-learning-SIEM-water-infrastructure/network/members). Supported by the French Naval Academy, the work shows that ML can successfully classify anomalies with >95% accuracy, improving the quality of fault diagnostic information, and improving response times to critical infrastructure problem resolution.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
