Sunday, October 4, 2026 Sign inSubscribe to The Brief →
Humanoid Threats

Security for the age of physical AI

Directory

Alias Robotics

European cybersecurity AI lab that began in 2018 securing robots, with endpoint protection for robots and the open-source CAI framework.

Category
Robot security specialist
Website
aliasrobotics.com
Last verified
October 4, 2026

What is Alias Robotics?

Alias Robotics is a European cybersecurity company, founded in the Basque Country in 2018 to secure robots. It has since grown into a cybersecurity AI lab, building security-focused AI models and agents alongside its original robot security products.

Key capabilities

  • RIS (Robot Immune System): endpoint protection designed for robotic systems.
  • CAI (Cybersecurity AI): an open-source framework for building AI security agents.
  • BlackBox: forensic tooling for tamper detection.
  • Security-specialized AI models that can run on-premises.

Why it matters for humanoid robot security

Alias Robotics is one of the few companies that started with robot security rather than adding it later. Its researchers co-authored a widely cited security assessment of the Unitree G1 humanoid, and in 2026 worked with IOActive on research that found 38 vulnerabilities in three consumer robots.

Where it fits in a humanoid robot security program

Alias Robotics sits closest to the robot itself. Its endpoint protection is aimed at the robot's onboard computers, and its research covers the full attack path from wireless setup to the AI assistant. For a humanoid program, it is most relevant at two points: security testing before a fleet goes live, and runtime monitoring on robots already deployed.

Who it is for

  • Humanoid and service robot manufacturers preparing a product launch
  • Enterprises evaluating a robot fleet purchase
  • Security teams that need independent robot testing or monitoring

Questions to ask Alias Robotics

  • Which humanoid or service robot platforms have you tested or protected so far?
  • Do you cover wireless setup, cloud links and the robot's AI assistant, not just the network?
  • Can findings be shared with the robot vendor under coordinated disclosure?
  • What does ongoing monitoring look like after deployment?

Similar listings

  • IOActive: Robot security research and testing

Sources

This listing is editorial and free; inclusion is not an endorsement. Work at Alias Robotics? Claim or update this listing.

Get the weekly Humanoid Threats Brief → Subscribe

The Humanoid Threats Brief

The weekly briefing on humanoid robot security.

New vulnerabilities, incidents, standards and defenses, with why each one matters. Built for security teams, robotics engineers and the people buying humanoids.

  • Every claim sourced. We link the CVE, the paper or the regulator, not rumors.
  • 5-minute read. One email a week, every Thursday.
  • Free. No spam, unsubscribe in one click.

Check your inbox to confirm your subscription.

Something went wrong. Please try again.

Read a recent storyUnitree G1 Vulnerabilities Explained: CVE-2026-76639 and CVE-2026-76640 →
100% primary-source linked 1 email a week