GraphCloak: Safeguarding Task-specific Knowledge within Graph-structured Data from Unauthorized Exploitation

TL;DR

GraphCloak introduces a novel graph-specific cloaking technique that applies subtle perturbations to both structure and features of graph data, effectively protecting against unauthorized GNN exploitation while remaining stealthy and stable across various settings.

Contribution

This work pioneers graph-oriented cloaking methods that are effective, stealthy, and stable, addressing a critical gap in protecting graph data from misuse.

Findings

Cloaking significantly reduces GNN performance on protected graphs.

The methods are stealthy, bypassing various inspection techniques.

Effective across diverse practical scenarios with limited knowledge.

Abstract

As Graph Neural Networks (GNNs) become increasingly prevalent in a variety of fields, from social network analysis to protein-protein interaction studies, growing concerns have emerged regarding the unauthorized utilization of personal data. Recent studies have shown that imperceptible poisoning attacks are an effective method of protecting image data from such misuse. However, the efficacy of this approach in the graph domain remains unexplored. To bridge this gap, this paper introduces GraphCloak to safeguard against the unauthorized usage of graph data. Compared with prior work, GraphCloak offers unique significant innovations: (1) graph-oriented, the perturbations are applied to both topological structures and descriptive features of the graph; (2) effective and stealthy, our cloaking method can bypass various inspections while causing a significant performance drop in GNNs trained on the cloaked graphs; and (3) stable across settings, our methods consistently perform effectively under a range of practical settings with limited knowledge. To address the intractable bi-level optimization problem, we propose two error-minimizing-based poisoning methods that target perturbations on the structural and feature space, along with a subgraph injection poisoning method. Our comprehensive evaluation of these methods underscores their effectiveness, stealthiness, and stability. We also delve into potential countermeasures and provide analytical justification for their effectiveness, paving the way for intriguing future research.