Modern Robotics Security For Heterogeneous Fleets

Ensure the flow of “good code” with robot-aware controls while automatically detecting and preventing suspicious activity.

Asimov replaces outdated signature-based approaches with modern security controls. Using dynamic threat analysis, machine-learned behavioral whitelisting, integrity controls and nano-segmentation, Asimov makes robotic applications more secure than ever possible before.


Continuous Component Assurance

Prevent unapproved components from running anywhere in your environment, based on known vulnerabilities, embedded secrets, OSS licensing, dynamic threat analysis, and secure node configuration.


Granular Monitoring & Logging

Monitors ROS nodes, hosts, and networks activity to detect and report on all policy violations, run/stop events, login events - all of which can be sent to your choice of SIEM (e.g, Splunk, ArcSight, and more).

control and monitor

Node-Level Application Firewall

Segments nodes by automatically creating dynamic firewall rules between services, ensuring that only whitelisted connections are allowed, and alerting on or blocking network traversal attempts.


Component-to-Host Drift Prevention

Enforces node immutability and detects any unapproved changes to running services by continuously comparing them to their originating states, including executables, privilege elevation, and system parameters.


Enforcing Least Privileges

Uses machine learning to automatically profile system behavior, whitelisting runtime parameters such as system calls, file access, network access, and executables, improving isolation and preventing privilege escalation.

control and monitor

CI/CD Integration

Asimov enables you to “shift left” security into early stages of development by scanning components as they are built, shortening the fix cycle for security issues. We provide native plug-ins as well as a CLI tool that automate scanning within CI tools such as Jenkins, Bamboo, and Azure DevOps. As a step in the build, developers can view scanning results and suggested mitigation from within a familiar environment.