Erasing the Wrong Thing: Conditional Attribute Leakage and Concept Erasure in Shared Foundation-Model Embeddings

arXiv:2611.25640v1 Announce Type: cross
Abstract: Medical-image embeddings are increasingly shared in place of raw images for authorized downstream tasks, yet they may reveal sensitive attributes. Standard concept-erasure methods target population-level guardedness. However, we prove that, when binary task and sensitive labels are associated, global and task-conditional linear guardedness cannot

[…]
Content was trimmed to protect the source. Please visit the original article for the full text.

This article has been indexed from cs.AI updates on arXiv.org

Read today’s AI news roundups »