✉news TechnologyRobotics first seen 1 d ago, last 1 d ago, peak #33
Robot experiment reveals trigger attacks on LLM planners
Original: Controlled robot experiment shows trigger attack and defense for LLM planners
Researchers describe a controlled robot experiment demonstrating a trigger attack against large language model planners, alongside a corresponding defense. The study shows how specific inputs can manipulate the planner's behavior in a robotic system, and how safeguards can mitigate the risk. The work highlights growing security concerns as LLM-based planners are deployed in autonomous robots.
Why now: Concerns about the safety and security of LLM-controlled robots are rising as the technology spreads.
Rank over time, top of the chart is #1. 2 snapshots from 1 d ago to 1 d ago.
Evidence
API: https://socialmediatrends-api.osmike.com/v1/trends/3038069