Adversarial Robustness of Probabilistic Network Embedding for Link Prediction

TL;DR

This paper investigates the robustness of probabilistic network embedding models, specifically Conditional Network Embedding, against small adversarial modifications for link prediction, highlighting vulnerabilities and proposing efficient identification methods.

Contribution

It introduces a novel approach to measure and analyze the adversarial robustness of CNE for link prediction, filling a research gap in network embedding security.

Findings

Successfully identifies most vulnerable links to adversarial attacks.

Efficient approximation method enables quick vulnerability assessment.

Empirical results confirm the effectiveness of the approach.

Abstract

In today's networked society, many real-world problems can be formalized as predicting links in networks, such as Facebook friendship suggestions, e-commerce recommendations, and the prediction of scientific collaborations in citation networks. Increasingly often, link prediction problem is tackled by means of network embedding methods, owing to their state-of-the-art performance. However, these methods lack transparency when compared to simpler baselines, and as a result their robustness against adversarial attacks is a possible point of concern: could one or a few small adversarial modifications to the network have a large impact on the link prediction performance when using a network embedding model? Prior research has already investigated adversarial robustness for network embedding models, focused on classification at the node and graph level. Robustness with respect to the link prediction downstream task, on the other hand, has been explored much less. This paper contributes to filling this gap, by studying adversarial robustness of Conditional Network Embedding (CNE), a state-of-the-art probabilistic network embedding model, for link prediction. More specifically, given CNE and a network, we measure the sensitivity of the link predictions of the model to small adversarial perturbations of the network, namely changes of the link status of a node pair. Thus, our approach allows one to identify the links and non-links in the network that are most vulnerable to such perturbations, for further investigation by an analyst. We analyze the characteristics of the most and least sensitive perturbations, and empirically confirm that our approach not only succeeds in identifying the most vulnerable links and non-links, but also that it does so in a time-efficient manner thanks to an effective approximation.