mlsanityData to 7 Oct 2026

Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods

arXiv 2111.03120 ↗First posted 4 Nov 2021cs.LG cs.AI cs.CLcited by 16

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

Abstract (arXiv)

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 prediction. These attacks craft adversarial additions or deletions at training time to cause model failure at test time. To select adversarial deletions, we propose to use the model-agnostic instance attribution methods from Interpretable Machine Learning, which identify the training instances that are most influential to a neural model's predictions on test instances. We use these influential triples as adversarial deletions. We further propose a heuristic method to replace one of the two entities in each influential triple to generate adversarial additions. Our experiments show that the proposed strategies outperform the state-of-art data poisoning attacks on KGE models and improve the MRR degradation due to the attacks by up to 62% over the baselines.

Key facts. Cited by 16 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 25 of its 42 references that are in the map. First posted on arXiv 4 Nov 2021.

Builds on

25 of 42 references.

References · 25

  1. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  2. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  3. 2016Complex Embeddings for Simple Link Predictioncited by 897
  4. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
  5. 2020Knowledge Graphscited by 619
  6. 2020Estimating Training Data Influence by Tracing Gradient Descentcited by 565
  7. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  8. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  9. 2018Adversarial Attack on Graph Structured Datacited by 300
  10. 2015A Review of Relational Machine Learning for Knowledge Graphscited by 264
  11. 2017A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applicationscited by 260
  12. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
13 more
  1. 2018Canonical Tensor Decomposition for Knowledge Base Completioncited by 150
  2. 2019On the Accuracy of Influence Functions for Measuring Group Effectscited by 146
  3. 2020Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functionscited by 144
  4. 2021Input Similarity from the Neural Network Perspectivecited by 78
  5. 2017KBGAN: Adversarial Learning for Knowledge Graph Embeddingscited by 62
  6. 2019Interaction Embeddings for Prediction and Explanation in Knowledge Graphscited by 40
  7. 2017Knowledge Base Completion: Baselines Strike Backcited by 39
  8. 2021An Empirical Comparison of Instance Attribution Methods for NLPcited by 35
  9. 2019Data Poisoning Attack against Knowledge Graph Embeddingcited by 34
  10. 2019Investigating Robustness and Interpretability of Link Prediction via Adversarial Modificationscited by 25
  11. 2017Adversarial Sets for Regularising Neural Link Predictorscited by 15
  12. 2020Explaining Neural Matrix Factorization with Gradient Rollbackcited by 5
  13. 2017On Inductive Abilities of Latent Factor Models for Relational Learningcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 10; 2025: 3; 2026: 1.

16 papers.

Sort:

By area:

  1. 2023Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraintscited by 21
  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. 2024Untargeted Adversarial Attack on Knowledge Graph Embeddingscited by 3
  6. 2024TWIG: Towards pre-hoc Hyperparameter Optimisation and Cross-Graph Generalisation via Simulated KGE Modelscited by 2
  7. 2024eXpath: Explaining Knowledge Graph Link Prediction with Ontological Closed Path Rulescited by 2
  8. 2024Resilience in Knowledge Graph Embeddingscited by 1
  9. 2025KGMark: A Diffusion Watermark for Knowledge Graphscited by 1
  10. 2026DRGW: Learning Disentangled Representations for Robust Graph Watermarkingcited by 1
  11. 2024Veni, Vidi, Vici: Solving the Myriad of Challenges before Knowledge Graph Learningcited by 0
  12. 2024From Latent to Lucid: Transforming Knowledge Graph Embeddings into Interpretable Structures with KGEPrismacited by 0
4 more
  1. 2024Performance Evaluation of Knowledge Graph Embedding Approaches under Non-adversarial Attackscited by 0
  2. 2024Extending TWIG: Zero-Shot Predictive Hyperparameter Selection for KGEs based on Graph Structurecited by 0
  3. 2025Unifying Post-hoc Explanations of Knowledge Graph Completionscited by 0
  4. 2025LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddingscited by 0