Black-box Node Injection Attack for Graph Neural Networks
원문 초록
Graph Neural Networks (GNNs) have drawn significant attentions over the years and been broadly applied to vital fields that require high security standard such as product recommendation and traffic forecasting. Under such scenarios, exploiting GNN's vulnerabilities and further downgrade its classification performance become highly incentive for adversaries. Previous attackers mainly focus on structural perturbations of existing graphs. Although they deliver promising results, the actual implementation needs capability of manipulating the graph connectivity, which is impractical in some circumstances. In this work, we study the possibility of injecting nodes to evade the victim GNN model, and unlike previous related works with white-box setting, we significantly restrict the amount of accessible knowledge and explore the black-box setting. Specifically, we model the node injection attack as a Markov decision process and propose GA2C, a graph reinforcement learning framework in the fashion of advantage actor critic, to generate realistic features for injected nodes and seamlessly merge them into the original graph following the same topology characteristics. Through our extensive experiments on multiple acknowledged benchmark datasets, we demonstrate the superior performance of our proposed GA2C over existing state-of-the-art methods. The data and source code are publicly accessible at: https://github.com/jumxglhf/GA2C.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
StealthRank: LLM Ranking Manipulation via Stealthy Prompt Optimization
FeatInsight: An Online ML Feature Management System on 4Paradigm Sage-Studio Platform
Recommender systems and reinforcement learning for human-building interaction and context-aware support: A text mining-driven review of scientific literature
Harnessing the Power of Semi-Structured Knowledge and LLMs with Triplet-Based Prefiltering for Question Answering
Estimating Heterogeneous Treatment Effects by Combining Weak Instruments and Observational Data
Using LLMs for the Extraction and Normalization of Product Attribute Values
토론
이 논문과 연결된 포럼 글이 아직 없습니다.