Unverified50% confidenceFactExact time
Research by VicOne LAB R7 points out that when the input information on which a robot's safety functions depend is itself tampered with, the robot may still respond correctly as designed yet perform dangerous actions.
1
Sources
50%
Confidence
Long-term
Relevance
10/27/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn a robot bug bounty event, VicOne LAB R7 researchers injected ROS 2/DDS messages into a robot that the organizers expected to remain stationary under security control settings, and the robot moved.75% similarUnverifiedA robot making errors or getting stuck on-site most likely indicates that it is running in genuine autonomous operation rather than a teleoperated demonstration.73% similarUnverifiedWhen a human steps in and resolves an error by other means, a negative signal should be sent, and the human fix should be written as a new note into the memory the bot recalls.71% similarUnverifiedThe recoverability of a robot task is not determined solely by the robot's current state, but depends on the pairing of the state with the type of intervention.70% similarUnverifiedWhen multiple robots run their own policies simultaneously, prediction errors amplify each other, potentially leading to collisions or deadlocks, which is especially pronounced in out-of-distribution (OOD) scenarios.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1104523API
curl https://kongchang.com/api/v1/knowledge/claims/1104523MCP
get_claim(id=1104523)