Researchers expose backdoor risks in AI-powered robot task planning
- MuTRAP links trigger words to harmful robot plans.
- The demonstrations used a model hand and a simulation.
- Researchers propose PROTEA to check task plans.
Researchers at Binghamton University demonstrated how a backdoor in a language model could make a robot’s task planner produce harmful instructions when given certain trigger words. The simulated examples involved cutting a model hand and putting a cat on a stove, highlighting risks when robotics firms use AI…