mlsanityData to 7 Oct 2026

Poisoning Knowledge Graph Embeddings via Relation Inference Patterns

arXiv 2111.06345 ↗First posted 11 Nov 2021cs.LG cs.AI cs.CLcited by 12

On the map: LLM safety and security → Backdoor and data poisoning attacks

Abstract (arXiv)

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.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security. Builds on 22 of its 35 references that are in the map. First posted on arXiv 11 Nov 2021.

Builds on

22 of 35 references.

References · 22

  1. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  2. 2016Complex Embeddings for Simple Link Predictioncited by 897
  3. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
  4. 2020Knowledge Graphscited by 619
  5. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  6. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  7. 2018Adversarial Attack on Graph Structured Datacited by 300
  8. 2017A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applicationscited by 260
  9. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
  10. 2018Adversarial Attacks on Node Embeddings via Graph Poisoningcited by 109
  11. 2020Complex Query Answering with Neural Link Predictorscited by 98
  12. 2017KBGAN: Adversarial Learning for Knowledge Graph Embeddingscited by 62
10 more
  1. 2015Traversing Knowledge Graphs in Vector Spacecited by 51
  2. 2017Knowledge Graph Embedding with Iterative Guidance from Soft Rulescited by 51
  3. 2019Interaction Embeddings for Prediction and Explanation in Knowledge Graphscited by 40
  4. 2019Data Poisoning Attack against Knowledge Graph Embeddingcited by 34
  5. 2019Investigating Robustness and Interpretability of Link Prediction via Adversarial Modificationscited by 25
  6. 2018From Knowledge Graph Embedding to Ontology Embedding? An Analysis of the Compatibility between Vector Space Representations and Rulescited by 19
  7. 2017On Multi-Relational Link Prediction with Bilinear Modelscited by 17
  8. 2017Adversarial Sets for Regularising Neural Link Predictorscited by 15
  9. 2020Explaining Neural Matrix Factorization with Gradient Rollbackcited by 5
  10. 2017On Inductive Abilities of Latent Factor Models for Relational Learningcited by 3

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 5; 2025: 3.

12 papers.

  1. 2025GraphRAG under Firecited by 23
  2. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
  3. 2024Predictive Multiplicity of Knowledge Graph Embeddings in Link Predictioncited by 9
  4. 2023On the Security Risks of Knowledge Graph Reasoningcited by 5
  5. 2023Schema First! Learn Versatile Knowledge Graph Embeddings by Capturing Semantics with MASCHInEcited by 3
  6. 2024Untargeted Adversarial Attack on Knowledge Graph Embeddingscited by 3
  7. 2022Explaining Link Predictions in Knowledge Graph Embedding Models with Influential Examplescited by 2
  8. 2025RAG Safety: Exploring Knowledge Poisoning Attacks to Retrieval-Augmented Generationcited by 2
  9. 2024Resilience in Knowledge Graph Embeddingscited by 1
  10. 2023Multi-Instance Adversarial Attack on GNN-Based Malicious Domain Detectioncited by 0
  11. 2024Performance Evaluation of Knowledge Graph Embedding Approaches under Non-adversarial Attackscited by 0
  12. 2025LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddingscited by 0