AI2Day
Tag

#adversarial attacks

2 stories taggedadversarial attacks.

A robot arm or mobile robot with its camera systems highlighted, displayed against a backdrop showing digital interference patterns, corrupted visual feeds, or
AI Security

Cómo los investigadores están engañando a los robots para que hagan lo incorrecto

Nuevas investigaciones demuestran que los robots impulsados por IA pueden ser manipulados a través de sus cámaras, datos de entrenamiento o sistemas inalámbricos, y las máquinas podrían no detectar nada anómalo.

5 min read
A close-up of a robotic arm in a factory performing a task, with digital overlay showing hidden network vulnerabilities and attack vectors invisible to physical
Robotics

The Hidden Weak Spot in Robot Safety That Nobody Is Talking About

Modern robots can be tricked into doing dangerous things without anything visibly breaking. Researchers say cybersecurity is the missing piece in how we keep AI-driven machines safe.

5 min read
© 2026 AI2Day