# Untargeted Adversarial Attack on Knowledge Graph Embeddings

arXiv: https://arxiv.org/abs/2405.10970 · HTML: https://mlsanity.com/paper/2405.10970/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 42 references that are in the map.
- First posted on arXiv 8 May 2024.

## Builds on (most cited first, 19 of 19)

- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [Adversarial Attacks on Neural Networks for Graph Data](https://mlsanity.com/paper/1805.07984/) (2018)
- [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019)
- [RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs](https://mlsanity.com/paper/2010.04029/) (2020)
- [Reinforcement Knowledge Graph Reasoning for Explainable Recommendation](https://mlsanity.com/paper/1906.05237/) (2019)
- [Fairness-Aware Explainable Recommendation over Knowledge Graphs](https://mlsanity.com/paper/2006.02046/) (2020)
- [Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning](https://mlsanity.com/paper/1903.08948/) (2019)
- [PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple Extraction](https://mlsanity.com/paper/2106.09895/) (2021)
- [Data Poisoning Attack against Knowledge Graph Embedding](https://mlsanity.com/paper/1904.12052/) (2019)
- [A Hard Label Black-box Adversarial Attack Against Graph Neural Networks](https://mlsanity.com/paper/2108.09513/) (2021)
- [Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications](https://mlsanity.com/paper/1905.00563/) (2019)
- [Answering Complex Questions by Joining Multi-Document Evidence with Quasi Knowledge Graphs](https://mlsanity.com/paper/1908.00469/) (2019)
- [Knowledge Graph Reasoning with Logics and Embeddings: Survey and Perspective](https://mlsanity.com/paper/2202.07412/) (2022)
- [Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods](https://mlsanity.com/paper/2111.03120/) (2021)
- [Poisoning Knowledge Graph Embeddings via Relation Inference Patterns](https://mlsanity.com/paper/2111.06345/) (2021)
- [Social Engineering in Cybersecurity: A Domain Ontology and Knowledge Graph Application Examples](https://mlsanity.com/paper/2106.01157/) (2021)

## Built on by (most cited first, 3 of 3)

- [RAG Safety: Exploring Knowledge Poisoning Attacks to Retrieval-Augmented Generation](https://mlsanity.com/paper/2507.08862/) (2025)
- [A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks](https://mlsanity.com/paper/2412.00789/) (2024)
- [Resilience in Knowledge Graph Embeddings](https://mlsanity.com/paper/2410.21163/) (2024)

## Abstract (arXiv)

Knowledge graph embedding (KGE) methods have achieved great success in handling various knowledge graph (KG) downstream tasks. However, KGE methods may learn biased representations on low-quality KGs that are prevalent in the real world. Some recent studies propose adversarial attacks to investigate the vulnerabilities of KGE methods, but their attackers are target-oriented with the KGE method and the target triples to predict are given in advance, which lacks practicability. In this work, we explore untargeted attacks with the aim of reducing the global performances of KGE methods over a set of unknown test triples and conducting systematic analyses on KGE robustness. Considering logic rules can effectively summarize the global structure of a KG, we develop rule-based attack strategies to enhance the attack efficiency. In particular,we consider adversarial deletion which learns rules, applying the rules to score triple importance and delete important triples, and adversarial addition which corrupts the learned rules and applies them for negative triples as perturbations. Extensive experiments on two datasets over three representative classes of KGE methods demonstrate the effectiveness of our proposed untargeted attacks in diminishing the link prediction results. And we also find that different KGE methods exhibit different robustness to untargeted attacks. For example, the robustness of methods engaged with graph neural networks and logic rules depends on the density of the graph. But rule-based methods like NCRL are easily affected by adversarial addition attacks to capture negative rules