Detecting Anomalies In Industrial Control Systems
Overview
Cybersecurity skill for detecting anomalies in industrial control systems. Follows industry best practices and security standards.
When to Use
Trigger phrases:
"detecting anomalies in industrial control systems"
"This skill covers deploying anomaly detection systems for industrial control env"
When deploying continuous monitoring for OT environments that lack intrusion detection
When building behavior-based detection to complement signature-based IDS in OT networks
When establishing baselines for deterministic SCADA communications to detect deviations
When integrating machine learning anomaly detection with OT security monitoring platforms
When investigating alerts from Nozomi Guardian or Dragos Platform that require deeper analysis
Do not use for signature-based detection of known exploits (see detecting-attacks-on-scada-systems), for IT network anomaly detection without OT protocols, or as a replacement for process safety systems (SIS).
When NOT to Use
- When you lack proper authorization for testing
- For production systems without change management
- When the task requires legal or compliance expertise beyond technical scope
Prerequisites
- Passive network monitoring sensors on OT network SPAN/TAP ports
- Minimum 2-4 weeks of baseline traffic capture during normal operations
- Python 3.9+ with scikit-learn, numpy, pandas for ML model training
- Process historian access for physical process correlation data
- Understanding of normal operational patterns including shift changes, batch processes, and maintenance windows
Workflow
# Example: IOC detection
import re
IOC_PATTERNS = {
"ip": r"\b(?:\d{1,3}\.){3}\d{1,3}\b",
"domain": r"\b[a-z0-9-]+\.[a-z]{2,}\b",
"hash_md5": r"\b[a-f0-9]{32}\b",
"hash_sha256": r"\b[a-f0-9]{64}\b",
}
def extract_iocs(text: str) -> dict:
return {k: re.findall(v, text) for k, v in IOC_PATTERNS.items()}
- Define Detection Scope — Identify the specific anomalies in industrial control systems techniques or indicators to hunt. Map to MITRE ATT&CK tactics/techniques where applicable.
- Collect Baseline Data — Gather historical logs and establish normal behavior patterns for anomalies in industrial control systems.
- Build Detection Queries — Write detection rules, Sigma rules, or SIEM queries targeting anomalies in industrial control systems indicators.
- Execute Hunts — Run queries against the collected data, starting with broad filters and narrowing down.
- Triage Results — Investigate alerts, filter false positives, and validate findings against known-good behavior.
- Document Findings — Record confirmed detections, IOCs, and affected systems. Update detection rules based on findings.
Tools
- SIEM Platform — Central log aggregation and query execution
- Sigma Rules — Vendor-agnostic detection rule format
- MITRE ATT&CK Navigator — Technique mapping and coverage analysis
Process
- Reconnaissance — Gather target information, identify attack surface, enumerate services
- Analysis/Exploitation — Execute the technique, analyze results, document findings
- Reporting — Document IOCs, write findings, provide remediation recommendations
Verification
Anti-Rationalization Table
| Rationalization |
Reality |
| "We are too small to be targeted" |
Automated attacks target everyone. Size does not matter. |
| "Security slows us down" |
A breach slows you down 100x more. Build security in from the start. |
| "We will fix it after launch" |
Vulnerabilities in production are exploited within hours. Fix before deploy. |
1---2name: detecting-anomalies-in-industrial-control-systems3description: Use when this skill covers deploying anomaly detection systems for industrial4 control environments using machine learning models trained on OT network baselines,5 physics-based process models, and behavioral analysis of industrial protocol communications.6 It addresses building normal behavior profiles for SCADA polling patterns, detecting7 deviations in Modbus/DNP3/OPC UA traffic, identifying rogue devices, and correlating8 network anomalies with physical process data from historians.9domain: cybersecurity10tags:11- ot-security12- ics13- scada14- industrial-control15- iec6244316- anomaly-detection17- machine-learning18subdomain: ot-ics-security19version: 1.0.020author: oyi7721license: Apache-2.022atlas_techniques:23- AML.T004324- AML.T001825nist_ai_rmf:26- MEASURE-2.727- MEASURE-2.528- MAP-5.129nist_csf:30- PR.IR-0131- DE.CM-0132- ID.AM-0533- GV.OC-0234category: cybersecurity35metadata:36 source: https://skillmd.com/skills/oyi77/detecting-anomalies-in-industrial-control-systems37---3839# Detecting Anomalies In Industrial Control Systems4041## Overview4243Cybersecurity skill for detecting anomalies in industrial control systems. Follows industry best practices and security standards.4445## When to Use46**Trigger phrases:**47- "detecting anomalies in industrial control systems"48- "This skill covers deploying anomaly detection systems for industrial control env"495051- When deploying continuous monitoring for OT environments that lack intrusion detection52- When building behavior-based detection to complement signature-based IDS in OT networks53- When establishing baselines for deterministic SCADA communications to detect deviations54- When integrating machine learning anomaly detection with OT security monitoring platforms55- When investigating alerts from Nozomi Guardian or Dragos Platform that require deeper analysis5657**Do not use** for signature-based detection of known exploits (see detecting-attacks-on-scada-systems), for IT network anomaly detection without OT protocols, or as a replacement for process safety systems (SIS).585960## When NOT to Use6162- When you lack proper authorization for testing63- For production systems without change management64- When the task requires legal or compliance expertise beyond technical scope656667## Prerequisites6869- Passive network monitoring sensors on OT network SPAN/TAP ports70- Minimum 2-4 weeks of baseline traffic capture during normal operations71- Python 3.9+ with scikit-learn, numpy, pandas for ML model training72- Process historian access for physical process correlation data73- Understanding of normal operational patterns including shift changes, batch processes, and maintenance windows7475## Workflow7677```python78# Example: IOC detection79import re8081IOC_PATTERNS = {82 "ip": r"\b(?:\d{1,3}\.){3}\d{1,3}\b",83 "domain": r"\b[a-z0-9-]+\.[a-z]{2,}\b",84 "hash_md5": r"\b[a-f0-9]{32}\b",85 "hash_sha256": r"\b[a-f0-9]{64}\b",86}8788def extract_iocs(text: str) -> dict:89 return {k: re.findall(v, text) for k, v in IOC_PATTERNS.items()}90```91921. **Define Detection Scope** — Identify the specific anomalies in industrial control systems techniques or indicators to hunt. Map to MITRE ATT&CK tactics/techniques where applicable.932. **Collect Baseline Data** — Gather historical logs and establish normal behavior patterns for anomalies in industrial control systems.943. **Build Detection Queries** — Write detection rules, Sigma rules, or SIEM queries targeting anomalies in industrial control systems indicators.954. **Execute Hunts** — Run queries against the collected data, starting with broad filters and narrowing down.965. **Triage Results** — Investigate alerts, filter false positives, and validate findings against known-good behavior.976. **Document Findings** — Record confirmed detections, IOCs, and affected systems. Update detection rules based on findings.9899## Tools100101- **SIEM Platform** — Central log aggregation and query execution102- **Sigma Rules** — Vendor-agnostic detection rule format103- **MITRE ATT&CK Navigator** — Technique mapping and coverage analysis104105106## Process1071081. **Reconnaissance** — Gather target information, identify attack surface, enumerate services1091. **Analysis/Exploitation** — Execute the technique, analyze results, document findings1101. **Reporting** — Document IOCs, write findings, provide remediation recommendations111112## Verification113114- [ ] All anomalies in industrial control systems procedures executed completely and documented115- [ ] Findings validated against multiple data sources116- [ ] False positives identified and filtered117- [ ] Results documented with evidence and timestamps118- [ ] Recommendations provided with risk-based prioritization119120## Anti-Rationalization Table121122| Rationalization | Reality |123|---|---|124| "We are too small to be targeted" | Automated attacks target everyone. Size does not matter. |125| "Security slows us down" | A breach slows you down 100x more. Build security in from the start. |126| "We will fix it after launch" | Vulnerabilities in production are exploited within hours. Fix before deploy. |