Adversarial Robustness of Representation Learning for Knowledge Graphs

by   Peru Bhardwaj, et al.
Trinity College Dublin

Knowledge graphs represent factual knowledge about the world as relationships between concepts and are critical for intelligent decision making in enterprise applications. New knowledge is inferred from the existing facts in the knowledge graphs by encoding the concepts and relations into low-dimensional feature vector representations. The most effective representations for this task, called Knowledge Graph Embeddings (KGE), are learned through neural network architectures. Due to their impressive predictive performance, they are increasingly used in high-impact domains like healthcare, finance and education. However, are the black-box KGE models adversarially robust for use in domains with high stakes? This thesis argues that state-of-the-art KGE models are vulnerable to data poisoning attacks, that is, their predictive performance can be degraded by systematically crafted perturbations to the training knowledge graph. To support this argument, two novel data poisoning attacks are proposed that craft input deletions or additions at training time to subvert the learned model's performance at inference time. These adversarial attacks target the task of predicting the missing facts in knowledge graphs using KGE models, and the evaluation shows that the simpler attacks are competitive with or outperform the computationally expensive ones. The thesis contributions not only highlight and provide an opportunity to fix the security vulnerabilities of KGE models, but also help to understand the black-box predictive behaviour of KGE models.


page 1

page 2

page 3

page 4


Learning Representations of Entities and Relations

Encoding facts as representations of entities and binary relationships b...

EvoLearner: Learning Description Logics with Evolutionary Algorithms

Classifying nodes in knowledge graphs is an important task, e.g., predic...

Poisoning Knowledge Graph Embeddings via Relation Inference Patterns

We study the problem of generating data poisoning attacks against Knowle...

Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods

Despite the widespread use of Knowledge Graph Embeddings (KGE), little i...

On a Generalized Framework for Time-Aware Knowledge Graphs

Knowledge graphs have emerged as an effective tool for managing and stan...

Reasoning on Knowledge Graphs with Debate Dynamics

We propose a novel method for automatic reasoning on knowledge graphs ba...

Debate Dynamics for Human-comprehensible Fact-checking on Knowledge Graphs

We propose a novel method for fact-checking on knowledge graphs based on...

Please sign up or login with your details

Forgot password? Click here to reset