VicOne’s new Radeis Extension for NVIDIA Isaac Sim lets robotics teams test cyberattack scenarios against their own robot models before deployment.
VicOne, a Physical AI cybersecurity solutions provider, has released the free VicOne Radeis Extension for NVIDIA Isaac Sim™, enabling robotics developers to test how selected cyber-safety attack scenarios could affect the behavior of their own robot models in simulation.
Available now, the extension lets teams introduce robot cyber-safety attack scenarios into their existing simulation workflows. Developers can then observe whether a robot deviates from its intended task, operating boundaries, or expected response, before exposing physical robots or real operating environments to unnecessary risk.
Built From DEF CON 34 Findings
The extension was shaped by findings from VicOne’s Physical AI Safety Stress Test capture-the-flag challenge at DEF CON 34’s Robotic Hacking Community, where security researchers tested how digital compromise could alter robot behavior under controlled conditions. The challenge examined attack paths across AI models, perception systems, cloud and API services, robotics communications, and embedded systems.
At DEF CON 34, 16 teams recorded 25 successful solves. Nearly every core AI and robotics cyber-safety challenge was solved at least once, with only one advanced embedded-systems challenge involving cryptography and firmware vulnerabilities left unsolved. VicOne said the results showed that behavior-changing risks can emerge across multiple layers of the robot stack, reinforcing the need to evaluate cybersecurity at the system level rather than assessing vulnerabilities in isolation.
“Robotics companies are moving from proving individual use cases to deploying robots at scale in real-world environments,” said Max Cheng, Chief Executive Officer of VicOne. “As that shift accelerates, the industry must validate not only whether robots function as designed, but whether they remain reliable when the digital systems they depend on are compromised. Cyber-safety validation must become a standard part of robotics development. By turning DEF CON research into repeatable simulation scenarios, we are helping developers address these risks earlier and build more resilient Physical AI at scale.”
What the Extension Does
VicOne says robot makers already invest heavily in functional testing, safety engineering, and simulation, but cyber-induced conditions can still fall outside conventional test plans. The company is using findings from the DEF CON challenge — including unsuccessful attempts and newly observed attack assumptions — to refine scenarios involving manipulated visual inputs, hijacked commands, poisoned AI policies, and exploited connected interfaces.
Using the free extension, developers can bring their own robot model and intended task into NVIDIA Isaac Sim; apply curated scenarios informed by VicOne’s Physical AI security research and DEF CON findings; validate whether a robot’s Vision-Language Model (VLM) remains resilient against adversarial visual prompts, malicious inputs, and sensor manipulation attempts that could lead to incorrect interpretations or unsafe decision-making; and repeat tests as models, software, sensors, communications, and control paths change over time.
NVIDIA Isaac Sim provides a physically based environment for designing, simulating, testing, and validating AI-driven robots. The VicOne Radeis Extension adds cyber-safety scenarios and behavioral-impact observation to existing simulation workflows, letting teams examine security-related edge cases before moving to physical testing or deployment.
A Starting Point, With a Paid Tier Beyond It
VicOne frames the free extension as a practical starting point for exploring cyber-to-physical risk, and says it can also help engineering, safety, and security teams discuss risk through visible robot outcomes rather than treating vulnerabilities as abstract software findings.
For organizations wanting a broader assessment, VicOne Radeis is also offered as a full pre-deployment cyber-safety validation solution that assesses component, system, and AI model risks, then evaluates how vulnerabilities and attack scenarios could affect the behavior of the integrated robot. The complete Radeis solution supports deeper investigation, remediation planning, release decisions, and compliance readiness.
The VicOne Radeis Extension for NVIDIA Isaac Sim is available now as a free download for developers using supported versions of NVIDIA Isaac Sim, via VicOne’s GitHub repository.