Why robot safety assurance must account for attacks that can change how a machine sees, decides, and acts. Robot safety has traditionally asked: Can a machine remain safe when something goes wrong? Physical AI raises a harder question: Can it remain safe when an attacker changes what it sees, decides, or does even when nothing appears to have failed? Modern robots perceive through multimodal sensors, interpret context using AI models, and translate those interpretations into physical action. As
Robot safety assurance has traditionally focused on preventing failures when systems malfunction, but a new concern has emerged: robots can be manipulated through cyberattacks that change what they perceive, decide, or do while appearing to function normally. These attacks can occur across three layers of a robot's system: corrupting AI models with hidden triggers during training, exploiting vulnerabilities in the underlying system infrastructure to override commands, and manipulating sensor inputs or reasoning at runtime. Addressing this risk requires extending safety assurance beyond functional safeguards to include cybersecurity practices throughout a robot's lifecycle, from design through operation, so that robots remain within safe boundaries even when under deliberate attack.

This week on Uncanny Valley, we dig into the latest prediction market buzz, Flock’s AI-powered police search tool, and how tech bros don’t know how to talk about “rouge” AI agents

Abliteration.AI is making powerful AI models without guardrails easier to access, arguing that giving defenders the same tools as bad actors could ultimately improve cybersecurity.

GPT-6 Astra is our most capable broadly deployed model and our first to reach the Critical level of cybersecurity capability under our Preparedness Framework.
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on Maven