Adversarial Attacks on Graph Neural Networks via Node Injections: A Hierarchical Reinforcement Learning Approach
Year: 2020
Type: conference-paper
Abstract: Graph Neural Networks (GNN) offer the powerful approach to node classification in complex networks across many domains including social media, E-commerce, and FinTech. However, recent studies show that GNNs are vulnerable to attacks aimed at adversely impacting their node classification performance. Existing studies of adversarial attacks on GNN focus primarily on manipulating the connectivity between existing nodes, a task that requires greater effort on the part of the attacker in real-world applications. In contrast, it is much more expedient on the part of the attacker to inject adversarial nodes, e.g., fake profiles with forged links, into existing graphs so as to reduce the performance of the GNN in classifying existing nodes.
Institution: Pennsylvania State University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Awards: BD Spokes: SPOKE: NORTHEAST: Collaborative Research: Integration of Environmental Factors and Causal Reasoning Approaches for Large-Scale Observational Health Research, SHF:Large:Collaborative Research: Inferring Software Specifications from Open Source Repositories by Leveraging Data and Collective Community Expertise, CIF21 DIBBs: EI: Virtual Data Collaboratory: A Regional Cyberinfrastructure for Collaborative Data Intensive Science, G4906924687, G713621388, G9000072794, G9000156441
OpenAlex ID: W3012846134