Graph Adversarial Immunization for Certifiable Robustness

TL;DR

This paper introduces graph adversarial immunization techniques that vaccinate parts of the graph structure to significantly enhance the certifiable robustness of graph neural networks against adversarial attacks, without sacrificing performance on clean data.

Contribution

It proposes novel edge-level and node-level immunization methods along with algorithms to efficiently identify immune nodes, improving robustness without performance loss.

Findings

AdvImmune-Node increases robust node ratio by up to 294%.

Immunizing only 5% of nodes yields substantial robustness gains.

Outperforms existing defenses against various adversarial attacks.

Abstract

Despite achieving great success, graph neural networks (GNNs) are vulnerable to adversarial attacks. Existing defenses focus on developing adversarial training or model modification. In this paper, we propose and formulate graph adversarial immunization, i.e., vaccinating part of graph structure to improve certifiable robustness of graph against any admissible adversarial attack. We first propose edge-level immunization to vaccinate node pairs. Unfortunately, such edge-level immunization cannot defend against emerging node injection attacks, since it only immunizes existing node pairs. To this end, we further propose node-level immunization. To avoid computationally intensive combinatorial optimization associated with adversarial immunization, we develop AdvImmune-Edge and AdvImmune-Node algorithms to effectively obtain the immune node pairs or nodes. Extensive experiments demonstrate the superiority of AdvImmune methods. In particular, AdvImmune-Node remarkably improves the ratio of robust nodes by 79%, 294%, and 100%, after immunizing only 5% of nodes. Furthermore, AdvImmune methods show excellent defensive performance against various attacks, outperforming state-of-the-art defenses. To the best of our knowledge, this is the first attempt to improve certifiable robustness from graph data perspective without losing performance on clean graphs, providing new insights into graph adversarial learning.