Trustcore offers a containerized, edge‑native platform that applies machine‑learning behavior analytics to IIoT devices, PLCs, SCADA systems, and LDAP directories for continuous real‑time monitoring. The solution detects anomalies, provides contextual alerts with root‑cause diagnostics, and exports risk scores via open APIs to SIEM, SOAR, and other security tools, supporting both on‑premise and SaaS deployments for industrial operators.
Funding
Funding not disclosed
Founders
Product
Problem
Industrial Internet of Things (IIoT) devices and operational technology (OT) environments lack built‑in security and real‑time health monitoring, making them vulnerable to ransomware, DDoS, credential‑stuffing, and other cyber attacks. When a breach or equipment fault occurs, operators receive fragmented alarms with little context, leading to prolonged downtime and costly production losses. Additionally, traditional IAM systems expose insider threats because they only verify credentials without continuous behavioral oversight.
Solution
Trustcore delivers a containerized, edge‑native platform—Trustcore BA—that applies advanced machine‑learning behavior analytics to data streams from PLCs, SCADA, LDAP directories, and other IIoT endpoints. The solution continuously profiles normal device and identity activity, detects deviations in real time, and generates instant alerts with automated root‑cause analysis. Operators can view granular telemetry and risk scores through a web dashboard or integrate findings via RESTful APIs into existing SIEM, SOAR, or SD‑WAN tools. The platform runs without additional hardware, supports on‑premise or SaaS deployment, and scales from single‑site factories to multi‑site utility networks, enabling proactive cyber‑defense and predictive maintenance.
Target Audience
Primary customers are OT managers, industrial manufacturers, water‑utility operators, and smart‑building facilities seeking to secure IIoT assets, as well as enterprise IAM teams that need continuous insider‑threat detection for directory services.
Features
- Containerized, zero‑touch installation that runs on edge gateways or virtual machines, eliminating the need for dedicated appliances.
- Machine‑learning inference engine that builds per‑device behavioral baselines and detects anomalies in network traffic, control packets, and LDAP log patterns.
- Real‑time alerting with contextual root‑cause diagnostics, including compromised credentials, failed binds, abnormal queries, and equipment performance degradation.
- Agentless or eBPF‑enabled data collection with < 2 % CPU overhead, suitable for high‑density OT environments.
- Integrated management console offering device provisioning, firmware version tracking, and customizable alert thresholds.
- Open APIs for seamless export of risk scores and events to SIEM, SOAR, and cloud security platforms (FHIR‑compatible for industrial data).
- Predictive failure modeling that schedules maintenance windows based on detected wear patterns and historical anomaly trends.
- Support for hybrid deployments (on‑premise or SaaS) and multi‑tenant isolation for managed service providers.