LGAICLSep 30, 2022

Adversarial Robustness of Representation Learning for Knowledge Graphs

arXiv:2210.00122v1h-index: 4Has Code
Originality Incremental advance
AI Analysis

This addresses security risks in high-stakes domains like healthcare and finance where KGE models are used, though it is incremental in highlighting vulnerabilities rather than proposing a fix.

The paper tackles the vulnerability of Knowledge Graph Embeddings (KGE) to data poisoning attacks, showing that state-of-the-art models can have their predictive performance degraded by crafted perturbations, with simpler attacks being competitive or outperforming more expensive ones.

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.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes