SOURCE-LINKED INTELLIGENCE

Seeing Less Is Not Seeing Safely: Privacy Leakage from Task-Scoped Robot Perception Exports

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Domestic robots rely on rich perception to operate in private homes, but privacy risk persists even when raw sensor data remain local. Structured representations exported to downstream planners, cloud services, logs, or learning pipelines can still reveal household information through semantics, geometry, spatial structure, and task targets. We introduce Task-Functional Perception Distillation (TFPD), a task-scoped representation-export framework that keeps rich perception local and profiles downstream exports according to task utility, direct exposure, and multiple residual inference risks. U

Read original source ↗ Open in workspace

recordType

paper

region

Global