Taipan: A Query-free Transfer-based Multiple Sensitive Attribute Inference Attack Solely from Auxiliary Graphs

Excerpt

arXiv:2602.06700v2 Announce Type: replace-cross Abstract: Graph-structured data underpin a wide spectrum of modern applications, yet their multiple sensitive attributes are not isolated but deeply coupled with graph topology. This coupling facilitates intersectional privacy leakage through attribute inference attacks (AIAs). Existing AIAs predominantly assume adversaries with two capabilities: (I) access to either auxiliary data sampled from the same distribution as the target or partial trainin