Revisiting Item Promotion in GNN-based Collaborative Filtering: A Masked Targeted Topological Attack Perspective

TL;DR

This paper introduces a novel targeted attack method on GNN-based collaborative filtering systems, reformulating item promotion as a topological attack and proposing techniques to improve attack effectiveness and efficiency.

Contribution

It presents the first targeted topological attack formulation for item promotion in GNN-based CF, addressing noisy gradients and enhancing attack success with a masked objective.

Findings

The attack effectively increases target item popularity.

The masked attack improves topological attack success.

The method is computationally efficient for large-scale systems.

Abstract

Graph neural networks (GNN) based collaborative filtering (CF) have attracted increasing attention in e-commerce and social media platforms. However, there still lack efforts to evaluate the robustness of such CF systems in deployment. Fundamentally different from existing attacks, this work revisits the item promotion task and reformulates it from a targeted topological attack perspective for the first time. Specifically, we first develop a targeted attack formulation to maximally increase a target item's popularity. We then leverage gradient-based optimizations to find a solution. However, we observe the gradient estimates often appear noisy due to the discrete nature of a graph, which leads to a degradation of attack ability. To resolve noisy gradient effects, we then propose a masked attack objective that can remarkably enhance the topological attack ability. Furthermore, we design a computationally efficient approach to the proposed attack, thus making it feasible to evaluate large-large CF systems. Experiments on two real-world datasets show the effectiveness of our attack in analyzing the robustness of GNN-based CF more practically.