RoboticsPhys.org Technologyabout 2 hours ago
Binghamton Team Reveals Robot Trojan Attack
4 min read
Researchers at Binghamton University demonstrated that hidden trigger words in large language models can cause robots to perform dangerous actions. The team presented two papers at the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems. They tested the attack using a Segway-based mobile robot programmed to mimic cutting a plastic fruit model.
Level
Hype check
Tap to vote and see what everyone thinks.
