Rethinking Robot Safety in the Age of AI

What happened

This article is brought to you by VicOne. Robot safety has traditionally asked: Can a machine remain safe when something goes wrong? Physical AI raises a harder question: Can a machine remain safe when an attacker changes what it sees, decides, or does even when nothing appears to have failed?

So a critical safety question today is whether Physical AI models remain within their task and safety boundaries under adversarial conditions. Simulation tools such as NVIDIA Isaac Sim, when paired with VicOne Radeis, can test the effects of manipulated inputs before deployment. VicOne Even a securely trained model can be subverted if the surrounding system stack is vulnerable.

In September 2025, researchers disclosed UniPwn, a Bluetooth exploit chain affecting quadruped and humanoid robots from a major manufacturer. Hardcoded cryptographic keys allowed traffic decryption, authentication checks were bypassed, and command injection enabled root-level execution. ” A compromised robot could scan nearby units and potentially affect an entire fleet. VicOne Middleware creates another exposure point.

Vulnerabilities in ROS 2 and DDS-based systems can enable arbitrary code execution or abuse unauthenticated topics to deliver malicious commands. With sufficient access, an attacker could override motor commands or replace AI model weights without directly attacking the model architecture. In this case, the components may still function as designed. What has changed is the trustworthiness of the commands flowing through the system.

Vulnerability management can help teams identify known risks before deployment, while continuous monitoring can surface emerging threats. At runtime, manipulating inputs that shape perception or reasoning may require neither firmware modification nor a network breach. In 2024, RoboPAIR demonstrated how carefully structured prompts could redirect LLM-controlled robots into unsafe trajectories.

BadRobot exposed a deeper architectural weakness: in several cases, a robot verbally refused a dangerous command while its motion controller executed the action anyway. Vision-based manipulation is equally powerful. VLAttack showed that an adversarial patch within the camera’s view could reduce a VLA model’s task success rate to zero. FreezeVLA showed that a single adversarial image could freeze a robot’s decision-making loop, making it unresponsive to subsequent instructions.

Why it matters

As AI and robotics continue to advance at an unprecedented pace, modern robots perceive through multimodal sensors, interpret context using AI models, and translate those interpretations into physical action. As they move into dynamic environments, their safety increasingly depends on the integrity of the data guiding their decisions. That dependence creates risks that conventional safety assessments may not fully capture.

Recent research has demonstrated that manipulating what a robot sees, hears, or interprets can influence its behavior without requiring direct control. Such manipulation can occur anywhere across its complex sensing and decision-making system — a layered attack surface encompassing training pipelines, system infrastructure, and runtime perception. In 2017, BadNets demonstrated that a model could behave normally under most conditions, yet fail in the presence of a specific hidden trigger.

In one example, a subtle pattern caused a stop sign to be misclassified as a speed limit sign without affecting the model’s behavior on other inputs. What began as a classification vulnerability has since evolved into action manipulation. At NeurIPS 2025, researchers introduced BadVLA a backdoor attack targeting Vision-Language-Action (VLA) models that allow robots to see, interpret instructions, and produce coordinated physical movement.

Rather than altering a single label, the attack caused conditional deviations in the robot’s action trajectory when a trigger was present. Without the trigger, the model largely preserved normal task performance, while the backdoor remained effective under task transfers and model fine-tuning. A related study in 2025, GoBA, showed that ordinary objects such as a coffee mug could serve as a reliable trigger.

The researchers reported a 97 percent attack success rate without degrading performance on clean inputs. A critical safety question today is whether Physical AI models remain within their task and safety boundaries under adversarial conditions. These studies expose a blind spot in model validation: A model may pass testing yet produce corrupted behavior when a hidden trigger appears in operation.

What to watch

Runtime assurance must therefore look beyond whether individual components remain available and assess whether cyber events are beginning to affect physical behavior. In each case, the camera may still work, the model may still run, and the controller may still respond. Yet the resulting behavior can be unsafe because the robot is acting on manipulated perception or reasoning.

The risks across these three layers reveal the missing layer in robot safety assurance: cybersecurity.