Spyke
technology·TechnologybyBeep

Self-driving cars, autonomous robots and drones, and other AI systems can get hijacked by custom road signs

  • Researchers demonstrate that misleading text in the real-world environment can hijack the decision-making of embodied AI systems without hacking their software.
  • Self-driving cars, autonomous robots and drones, and other AI systems that use cameras may be vulnerable to these attacks.
  • The study presents the first academic exploration of environmental indirect prompt injection attacks against embodied AI systems.

::: spoiler Photos

:::

Self-driving cars, autonomous robots and drones, and other AI systems can get hijacked by custom road signshttps://news.ucsc.edu/2026/01/misleading-text-can-hijack-ai-enabled-robots/Open linkView original on lemmus.org

An article about the dangers of AI starts off with an AI generated comic about the dangers of AI.

111

And it can't even get the colour of the drone or number of propellers it has consistent between two panels

8
feddit.org

the first academic exploration

I have read about it, years ago. And there are jokes about it that are many years old.

This one against speed cams, for example:

24

Could it really be as simpe as that? yes, according to the article. AI sucks so hard, who let it out of a laboratory?

18

One time I saw a 30mph sign spray painted to say 88mph speed limit. Good thing it was before self driving cars of that would have been crazy.

13

Misleading text in the physical world can hijack AI-enabled robots, cybersecurity study shows

Eh, yes? Hasn't that been like that since day 1?

1

You reached the end

Self-driving cars, autonomous robots and drones, and other AI systems can get hijacked by custom road signs | Spyke