Data Poisoning Attack against Knowledge Graph Embedding

Abstract

Knowledge graph embedding (KGE) is a technique for learning continuous embeddings for entities and relations in the knowledge graph.Due to its benefit to a variety of downstream tasks such as knowledge graph completion, question answering and recommendation, KGE has gained significant attention recently. Despite its effectiveness in a benign environment, KGE' robustness to adversarial attacks is not well-studied. Existing attack methods on graph data cannot be directly applied to attack the embeddings of knowledge graph due to its heterogeneity. To fill this gap, we propose a collection of data poisoning attack strategies, which can effectively manipulate the plausibility of arbitrary targeted facts in a knowledge graph by adding or deleting facts on the graph. The effectiveness and efficiency of the proposed attack strategies are verified by extensive evaluations on two widely-used benchmarks.

Fix typos and version conflicts

References in corpus (7)

• Semi-Supervised Classification with Graph Convolutional Networks
• Adversarial Attacks on Neural Networks for Graph Data
• Adversarial Attack on Graph Structured Data
• Fast Gradient Attack on Network Embedding
• TransA: An Adaptive Approach for Knowledge Graph Embedding
• Data Poisoning Attack against Unsupervised Node Embedding Methods
• Learning Multi-Relational Semantics Using Neural-Embedding Models

Cited by in corpus (2)

• Adversarial Attack and Defense on Graph Data: A Survey
• Data Poisoning Attacks on Neighborhood-based Recommender Systems