paper-with-me

홈 › Papers

Poisoning Knowledge Graph Embeddings via Relation Inference Patterns

2021-11-11 · ACL 2021 5 · Peru Bhardwaj, John Kelleher, Luca Costabello, Declan O'Sullivan

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.

📄 PDF Abstract BibTeX arXiv:2111.06345

Code (1)

perubhardwaj/inferenceattack 공식 구현 pytorch

Tasks

Data PoisoningGraph EmbeddingKnowledge Graph EmbeddingKnowledge Graph EmbeddingsKnowledge GraphsLink PredictionPredictionRelation

Similar Papers 제목 키워드 기반

Data Poisoning Attack against Knowledge Graph Embedding

2019-04-26 · Hengtong Zhang, Tianhang Zheng, Jing Gao, Chenglin Miao 외

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, …

Data PoisoningGraph EmbeddingKnowledge Graph CompletionKnowledge Graph Embedding+1

Adversarial Robustness of Representation Learning for Knowledge Graphs

2022-09-30 · Peru Bhardwaj

Knowledge graphs represent factual knowledge about the world as relationships between concepts and are critical for intelligent decision making in enterprise applications. New knowledge is inferred from the existing fact…

Adversarial RobustnessData PoisoningDecision MakingKnowledge Graph Embeddings+2

GraphRAG under Fire

2025-01-23 · Jiacheng Liang, Yuhui Wang, Changjiang Li, Rongyi Zhu 외

GraphRAG advances retrieval-augmented generation (RAG) by structuring external knowledge as multi-scale knowledge graphs, enabling language models to integrate both broad context and granular details in their generation.…

Knowledge GraphsRAGRelationRetrieval+1

InGram: Inductive Knowledge Graph Embedding via Relation Graphs

2023-05-31 · Jaejun Lee, Chanyoung Chung, Joyce Jiyoung Whang

Inductive knowledge graph completion has been considered as the task of predicting missing triplets between new entities that are not observed during training. While most inductive knowledge graph completion methods assu…

Entity EmbeddingsGraph EmbeddingInductive knowledge graph completionInductive Learning+5

Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods

2021-11-04 · EMNLP 2021 11 · Peru Bhardwaj, John Kelleher, Luca Costabello, Declan O'Sullivan

Despite the widespread use of Knowledge Graph Embeddings (KGE), little is known about the security vulnerabilities that might disrupt their intended behaviour. We study data poisoning attacks against KGE models for link …

Data PoisoningInterpretable Machine LearningKnowledge Graph EmbeddingsLink Prediction