SOURCE-LINKED INTELLIGENCE

Privacy-Preserving Deep Joint Source-Channel Coding with In-Loop Concept Erasure

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Deep joint source-channel coding (DeepJSCC) transmits learned semantic features efficiently but can leak sensitive attributes such as gender, race, or speaker identity. We propose LEAPSC (LEACE-in-the-loop privacy for semantic communication), whose core contribution is the integration of in-loop least-squares concept erasure (LEACE) within a variational information bottleneck (VIB) encoder. By periodically refitting the projection operator during training, LEAPSC couples the encoder dynamics to the erasure mechanism, driving attribute-conditional mean differences toward zero within each task-l

Read original source ↗ Open in workspace

recordType

paper

region

Global