Untargeted Adversarial Attack on Knowledge Graph Embeddings

TL;DR

This paper introduces untargeted adversarial attack strategies on knowledge graph embeddings, using rule-based methods to systematically reduce the performance of various KGE models, revealing their differing robustness.

Contribution

The work proposes novel rule-based untargeted attack techniques that do not rely on specific target triples, enhancing the practicality of adversarial attacks on KGE methods.

Findings

Untargeted attacks significantly reduce link prediction accuracy.

Different KGE models show varying robustness to attacks.

Graph density influences the effectiveness of certain attack strategies.

Abstract

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