Unsupervised Euclidean Distance Attack on Network Embedding

TL;DR

This paper introduces an unsupervised genetic algorithm-based attack method that disrupts network embeddings by maximizing Euclidean distance between node pairs, aiming to hinder various graph analysis algorithms.

Contribution

It presents a novel unsupervised attack strategy on network embeddings using genetic algorithms to manipulate Euclidean distances without requiring labels.

Findings

Effective in disturbing network embedding structures

Universal attack applicable to multiple network algorithms

Does not rely on labeled data

Abstract

Considering the wide application of network embedding methods in graph data mining, inspired by the adversarial attack in deep learning, this paper proposes a Genetic Algorithm (GA) based Euclidean Distance Attack strategy (EDA) to attack the network embedding, so as to prevent certain structural information from being discovered. EDA focuses on disturbing the Euclidean distance between a pair of nodes in the embedding space as much as possible through minimal modifications of the network structure. Since a large number of downstream network algorithms, such as community detection and node classification, rely on the Euclidean distance between nodes to evaluate the similarity between them in the embedding space, EDA can be considered as a universal attack on a variety of network algorithms. Different from traditional supervised attack strategies, EDA does not need labeling information, and, in other words, is an unsupervised network embedding attack method.