Poisoning Knowledge Graph Embeddings via Relation Inference Patterns

by   Peru Bhardwaj, et al.
ADAPT Centre

We study the problem of generating data poisoning attacks against Knowledge Graph Embedding (KGE) models for the task of link prediction in knowledge graphs. To poison KGE models, we propose to exploit their inductive abilities which are captured through the relationship patterns like symmetry, inversion and composition in the knowledge graph. Specifically, to degrade the model's prediction confidence on target facts, we propose to improve the model's prediction confidence on a set of decoy facts. Thus, we craft adversarial additions that can improve the model's prediction confidence on decoy facts through different inference patterns. Our experiments demonstrate that the proposed poisoning attacks outperform state-of-art baselines on four KGE models for two publicly available datasets. We also find that the symmetry pattern based attacks generalize across all model-dataset combinations which indicates the sensitivity of KGE models to this pattern.


Graph Pattern Entity Ranking Model for Knowledge Graph Completion

Knowledge graphs have evolved rapidly in recent years and their usefulne...

Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods

Despite the widespread use of Knowledge Graph Embeddings (KGE), little i...

Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction

Knowledge graph embedding, which aims to represent entities and relation...

Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications

Representing entities and relations in an embedding space is a well-stud...

Adversarial Robustness of Representation Learning for Knowledge Graphs

Knowledge graphs represent factual knowledge about the world as relation...

Dynamic Relation Repairing for Knowledge Enhancement

Dynamic relation repair aims to efficiently validate and repair the inst...

Bi-Link: Bridging Inductive Link Predictions from Text via Contrastive Learning of Transformers and Prompts

Inductive knowledge graph completion requires models to comprehend the u...

Please sign up or login with your details

Forgot password? Click here to reset