Misleading text in the physical world can hijack AI-enabled robots, cybersecurity study shows
January 21, 2026
January 21, 2026
SANTA CRUZ, California, Jan. 21 -- The University of California Santa Cruz campus issued the following news:
* * *
Misleading text in the physical world can hijack AI-enabled robots, cybersecurity study shows
* 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 th . . .
* * *
Misleading text in the physical world can hijack AI-enabled robots, cybersecurity study shows
* 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 th . . .
