Towards Revealing Parallel Adversarial Attack on Politician Socialnet of Graph Structure

Abstract

Socialnet becomes an important component in real life, drawing a lot of study issues of security and safety. Recently, for the features of graph structure in socialnet, adversarial attacks on node classification are exposed, and automatic attack methods such as fast gradient attack (FGA) and NETTACK are developed for per-node attacks, which can be utilized for multinode attacks in a sequential way. However, due to the overlook of perturbation influence between different per-node attacks, the above sequential method does not guarantee a global attack success rate for all target nodes, under a fixed budget of perturbation. In this paper, we propose a parallel adversarial attack framework on node classification. We redesign new loss function and objective function for nonconstraint and constraint perturbations, respectively. Through constructing intersection and supplement mechanisms of perturbations, we then integrate node filtering-based P-FGA and P-NETTACK in a unified framework, finally realizing parallel adversarial attacks. Experiments on politician socialnet dataset Polblogs with detailed analysis are conducted to show the effectiveness of our approach.

A Hard Label Black-box Adversarial Attack Against Graph Neural Networks

“…For node classification, the attacks can be divided into two categories, i.e., optimization based ones [32,42,44,52] and heuristic based ones that leverage greedy algorithms [9,50] or reinforcement learning (RL) [13,41]. In order to develop an optimization based method, the attacker formulates the attack as an optimization problem and solves it via typical techniques such as gradient descent.…”