mlsanityData to 7 Oct 2026

Membership Inference Attacks on Knowledge Graphs

arXiv 2104.08273 ↗First posted 16 Apr 2021cs.AI cs.CLcited by 11

On the map: LLM safety and security → Membership inference attacks

Abstract (arXiv)

Membership inference attacks (MIAs) infer whether a specific data record is used for target model training. MIAs have provoked many discussions in the information security community since they give rise to severe data privacy issues, especially for private and sensitive datasets. Knowledge Graphs (KGs), which describe domain-specific subjects and relationships among them, are valuable and sensitive, such as medical KGs constructed from electronic health records. However, the privacy threat to knowledge graphs is critical but rarely explored. In this paper, we conduct the first empirical evaluation of privacy threats to knowledge graphs triggered by knowledge graph embedding methods (KGEs). We propose three types of membership inference attacks: transfer attacks (TAs), prediction loss-based attacks (PLAs), and prediction correctness-based attacks (PCAs), according to attack difficulty levels. In the experiments, we conduct three inference attacks against four standard KGE methods over three benchmark datasets. In addition, we also propose the attacks against medical KG and financial KG. The results demonstrate that the proposed attack methods can easily explore the privacy leakage of knowledge graphs.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Placed in Membership inference attacks, one of 12 directions in LLM safety and security. Builds on 32 of its 56 references that are in the map. First posted on arXiv 16 Apr 2021.

Builds on

32 of 56 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Membership Inference Attacks on Machine Learning: A Survey14 Mar

Other references · 31

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  3. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  4. 2016Complex Embeddings for Simple Link Predictioncited by 897
  5. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 893
  6. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  7. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
  8. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  9. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  10. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 273
  11. 2015Holographic Embeddings of Knowledge Graphscited by 181
  12. 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 177
19 more
  1. 2019Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inferencecited by 168
  2. 2019Privacy Risks of Securing Machine Learning Models against Adversarial Examplescited by 136
  3. 2019Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphscited by 125
  4. 2019Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learningcited by 117
  5. 2018Stealing Hyperparameters in Machine Learningcited by 115
  6. 2020Quantifying Privacy Leakage in Graph Embeddingcited by 82
  7. 2021Membership Inference Attack on Graph Neural Networkscited by 81
  8. 2021Node-Level Membership Inference Attacks Against Graph Neural Networkscited by 80
  9. 2020Relational Message Passing for Knowledge Graph Completioncited by 61
  10. 2021Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!cited by 51
  11. 2018Differentially Private Data Generative Modelscited by 33
  12. 2017LOGAN: Membership Inference Attacks Against Generative Modelscited by 28
  13. 2017Towards Measuring Membership Privacycited by 27
  14. 2019Probability Calibration for Knowledge Graph Embedding Modelscited by 20
  15. 2020Natural Backdoor Attack on Text Datacited by 18
  16. 2016STransE: a novel embedding model of entities and relationships in knowledge basescited by 17
  17. 2020Membership Inference Attacks and Defenses in Classification Modelscited by 14
  18. 2019Privacy Attacks on Network Embeddingscited by 4
  19. 2019Robust Membership Encoding: Inference Attacks and Copyright Protection for Deep Learningcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 2; 2023: 2; 2024: 3; 2025: 0; 2026: 3.

11 papers.

  1. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  2. 2021Source Inference Attacks in Federated Learningcited by 31
  3. 2023A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applicationscited by 22
  4. 2022A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protectioncited by 20
  5. 2024Model Inversion Attacks: A Survey of Approaches and Countermeasurescited by 11
  6. 2023Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embeddingcited by 7
  7. 2024A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasurescited by 6
  8. 2024Inference Attacks: A Taxonomy, Survey, and Promising Directionscited by 2
  9. 2026Impact of Graph Structure on Membership-Inference Risk for Graph Neural Networkscited by 1
  10. 2026Inferring Sensitive Attributes from Knowledge Graph Embeddings: Attack and Defense Strategiescited by 0
  11. 2026Bayesian Membership Privacy for Graph Neural Networkscited by 0