Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing

Abstract

Community detection plays a key role in understanding graph structure. However, several recent studies showed that community detection is vulnerable to adversarial structural perturbation. In particular, via adding or removing a small number of carefully selected edges in a graph, an attacker can manipulate the detected communities. However, to the best of our knowledge, there are no studies on certifying robustness of community detection against such adversarial structural perturbation. In this work, we aim to bridge this gap. Specifically, we develop the first certified robustness guarantee of community detection against adversarial structural perturbation. Given an arbitrary community detection method, we build a new smoothed community detection method via randomly perturbing the graph structure. We theoretically show that the smoothed community detection method provably groups a given arbitrary set of nodes into the same community (or different communities) when the number of edges added/removed by an attacker is bounded. Moreover, we show that our certified robustness is tight. We also empirically evaluate our method on multiple real-world graphs with ground truth communities.

arXiv commentAccepted by WWW'20; This is technical report version

References in corpus (15)

• Fast unfolding of communities in large networks
• Community structure in social and biological networks
• Modularity and community structure in networks
• Semi-Supervised Classification with Graph Convolutional Networks
• Resolution limit in community detection
• Adversarial Attacks on Neural Networks for Graph Data
• Certified Defenses against Adversarial Examples
• Adversarial Attacks on Graph Neural Networks via Meta Learning
• Adversarial Attacks on Node Embeddings via Graph Poisoning
• Adversarial Attack on Graph Structured Data
• Adversarial Examples on Graph Data: Deep Insights into Attack and Defense
• Certifiable Robustness to Graph Perturbations
• Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers
• Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing
• Attacking Graph-based Classification via Manipulating the Graph Structure

Cited by in corpus (2)

• Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies
• Certified Robustness of Graph Classification against Topology Attack with Randomized Smoothing