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

2026-02-06

AI Summary

This work addresses the limitations of existing graph attribute inference attacks, which rely on model queries and are thus constrained by regulatory, budgetary, and detection risks, while also overlooking the inherent leakage of multiple sensitive attributes embedded in publicly available graph structures. To overcome these challenges, we propose Taipan, the first query-free, transfer learning–based framework for multi-attribute inference that leverages only public graph data to infer multiple sensitive attributes. Taipan introduces a novel hierarchical attack knowledge routing mechanism to model complex inter-attribute dependencies and integrates a prompt-guided prototype optimization strategy to mitigate negative transfer, enabling effective attacks across heterogeneous distributions and feature dimensions. Extensive experiments demonstrate that Taipan achieves strong performance under in-distribution, out-of-distribution, and distribution-shift settings, and remains effective even against differentially private graph models.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Data transparency and provenance

Abstract

Graph-structured data underpin a wide spectrum of modern applications. However, complex graph topologies and homophilic patterns can facilitate attribute inference attacks (AIAs) by enabling sensitive information leakage to propagate across local neighborhoods. Existing AIAs predominantly assume that adversaries can probe sensitive attributes through repeated model queries. Such assumptions are often impractical in real-world settings due to stringent data protection regulations, prohibitive query budgets, and heightened detection risks, especially when inferring multiple sensitive attributes. More critically, this model-centric perspective obscures a pervasive blind spot: \textbf{intrinsic multiple sensitive information leakage arising solely from publicly released graphs.} To exploit this unexplored vulnerability, we introduce a new attack paradigm and propose \textbf{Taipan, the first query-free transfer-based attack framework for multiple sensitive attribute inference attacks on graphs (G-MSAIAs).} Taipan integrates \emph{Hierarchical Attack Knowledge Routing} to capture intricate inter-attribute correlations, and \emph{Prompt-guided Attack Prototype Refinement} to mitigate negative transfer and performance degradation. We further present a systematic evaluation framework tailored to G-MSAIAs. Extensive experiments on diverse real-world graph datasets demonstrate that Taipan consistently achieves strong attack performance across same-distribution settings and heterogeneous similar- and out-of-distribution settings with mismatched feature dimensionalities, and remains effective even under rigorous differential privacy guarantees. Our findings underscore the urgent need for more robust multi-attribute privacy-preserving graph publishing methods and data-sharing practices.

Problem

• attribute inference attack
• graph privacy
• sensitive attribute leakage
• query-free attack
• multiple sensitive attributes

Innovation

• query-free attack
• transfer-based inference
• multiple sensitive attributes
• graph privacy leakage
• hierarchical knowledge routing