Cluster-Aware Attacks on Graph Watermarks

2025-04-24

AI Summary

Community detection–guided graph watermarking evasion attacks exploit graph community structure to launch targeted perturbations that undermine watermark ownership attribution. Method: This work introduces, for the first time, a cluster-aware threat model formalizing how adversaries leverage community structure for such attacks; proposes two novel community-aware attack strategies; and designs a lightweight watermark node embedding enhancement method that leverages cross-community distribution—improving robustness without structural overhead or runtime latency. Contribution/Results: Experiments show that the proposed attacks reduce watermark attribution accuracy by up to 80% on sparse graphs; the enhancement method boosts adversarial robustness by up to 60% on dense graphs, with no additional distortion or computational delay. This work establishes a new paradigm for structure-aware graph watermarking security modeling and defense.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Graph-based Machine Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Data from domains such as social networks, healthcare, finance, and cybersecurity can be represented as graph-structured information. Given the sensitive nature of this data and their frequent distribution among collaborators, ensuring secure and attributable sharing is essential. Graph watermarking enables attribution by embedding user-specific signatures into graph-structured data. While prior work has addressed random perturbation attacks, the threat posed by adversaries leveraging structural properties through community detection remains unexplored. In this work, we introduce a cluster-aware threat model in which adversaries apply community-guided modifications to evade detection. We propose two novel attack strategies and evaluate them on real-world social network graphs. Our results show that cluster-aware attacks can reduce attribution accuracy by up to 80% more than random baselines under equivalent perturbation budgets on sparse graphs. To mitigate this threat, we propose a lightweight embedding enhancement that distributes watermark nodes across graph communities. This approach improves attribution accuracy by up to 60% under attack on dense graphs, without increasing runtime or structural distortion. Our findings underscore the importance of cluster-topological awareness in both watermarking design and adversarial modeling.

Problem

• Explores cluster-aware attacks on graph watermarking systems
• Investigates community-guided modifications to evade watermark detection
• Proposes defense against attacks by distributing watermark across communities

Innovation

• Cluster-aware threat model for graph watermarking
• Lightweight embedding enhancement across communities
• Community-guided modifications to evade detection