# Inferring Sensitive Attributes from Knowledge Graph Embeddings: Attack and Defense Strategies

arXiv: https://arxiv.org/abs/2605.19644 · HTML: https://mlsanity.com/paper/2605.19644/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 19 May 2026.

## Builds on (most cited first, 12 of 12)

- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs](https://mlsanity.com/paper/2010.04029/) (2020)
- [FedE: Embedding Knowledge Graphs in Federated Setting](https://mlsanity.com/paper/2010.12882/) (2020)
- [Graph Embedding for Recommendation against Attribute Inference Attacks](https://mlsanity.com/paper/2101.12549/) (2021)
- [Benchmark and Best Practices for Biomedical Knowledge Graph Embeddings](https://mlsanity.com/paper/2006.13774/) (2020)
- [Membership Inference Attacks on Knowledge Graphs](https://mlsanity.com/paper/2104.08273/) (2021)
- [Knowledge Graph Embedding: An Overview](https://mlsanity.com/paper/2309.12501/) (2023)
- [Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding](https://mlsanity.com/paper/2304.02932/) (2023)
- [Survey and Open Problems in Privacy Preserving Knowledge Graph: Merging, Query, Representation, Completion and Applications](https://mlsanity.com/paper/2011.10180/) (2020)
- [RulE: Knowledge Graph Reasoning with Rule Embedding](https://mlsanity.com/paper/2210.14905/) (2022)
- [RecKG: Knowledge Graph for Recommender Systems](https://mlsanity.com/paper/2501.03598/) (2025)
- [Onto-DP: Constructing Neighborhoods for Differential Privacy on Ontological Databases](https://mlsanity.com/paper/2602.15614/) (2026)

## Abstract (arXiv)

Knowledge Graphs (KGs) are a powerful representation of linked data, offering flexibility, semantic richness, and support for knowledge enrichment and reasoning. They help data owners organize and exploit heterogeneous data to provide insightful services (e.g., recommendations), yet real-world KGs are often incomplete, hiding true facts or missing valuable insights. Knowledge graph embedding techniques are commonly used to infer valuable missing information. However, reasoning over KGs can inadvertently expose sensitive user information, even when such data is not explicitly stored. In this work, we investigate the privacy risks associated with KGE-based reasoning, focusing on attribute inference attacks where adversaries attempt to deduce sensitive user attributes from seemingly non-sensitive outputs. We propose and evaluate a framework that mitigates these privacy risks by applying post processing sanitization techniques to KGE outputs. Preliminary results demonstrate the effectiveness of these attacks on the outputs of KGE models, and explore the trade-off between recommendation quality and privacy protection when applying randomization based approaches, highlighting the need to experiment with more advanced techniques in future work to address this issue.