A whispered word of command could allow spies to take control of an army of robots, security researchers have warned.
The vulnerability in humanoid robots, which could see disruptive behaviour spread from one machine to another and cause widespread chaos, was exposed a few weeks ago at the GEEKCon competition in Shanghai.
Since its inception in 2014, GEEKCon has successfully held 17 events, bringing together “white-hat hackers” from China, the US, Russia and elsewhere to compete.
Advertisement
Security researchers Qu Shipei and Xu Zikai from DARKNAVY, a cybersecurity research group, showed how to take control of a robot using just a verbal command and then used that compromised robot to infect others, ultimately manipulating them to carry out malicious instructions.
The test subject was a domestically produced humanoid robot priced at around 100,000 yuan (US$14,200). The participants exploited a flaw within the robot’s built-in large-model agent, a type of AI system, to launch an attack.
Advertisement
Through voice interaction, they triggered and gained access, seizing full control of an internet-connected robot.