Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks

01/05/2023
by   Yan Scholten, et al.
0

Randomized smoothing is one of the most promising frameworks for certifying the adversarial robustness of machine learning models, including Graph Neural Networks (GNNs). Yet, existing randomized smoothing certificates for GNNs are overly pessimistic since they treat the model as a black box, ignoring the underlying architecture. To remedy this, we propose novel gray-box certificates that exploit the message-passing principle of GNNs: We randomly intercept messages and carefully analyze the probability that messages from adversarially controlled nodes reach their target nodes. Compared to existing certificates, we certify robustness to much stronger adversaries that control entire nodes in the graph and can arbitrarily manipulate node features. Our certificates provide stronger guarantees for attacks at larger distances, as messages from farther-away nodes are more likely to get intercepted. We demonstrate the effectiveness of our method on various models and datasets. Since our gray-box certificates consider the underlying graph structure, we can significantly improve certifiable robustness by applying graph sparsification.

READ FULL TEXT

page 5

page 31

page 32

research
07/05/2021

Elastic Graph Neural Networks

While many existing graph neural networks (GNNs) have been proven to per...
research
02/08/2022

Boosting Graph Neural Networks by Injecting Pooling in Message Passing

There has been tremendous success in the field of graph neural networks ...
research
08/29/2020

Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More

Existing techniques for certifying the robustness of models for discrete...
research
04/27/2022

SSR-GNNs: Stroke-based Sketch Representation with Graph Neural Networks

This paper follows cognitive studies to investigate a graph representati...
research
06/06/2023

How does over-squashing affect the power of GNNs?

Graph Neural Networks (GNNs) are the state-of-the-art model for machine ...
research
11/19/2022

Tired of Over-smoothing? Stress Graph Drawing Is All You Need!

In designing and applying graph neural networks, we often fall into some...
research
11/25/2022

Invariance-Aware Randomized Smoothing Certificates

Building models that comply with the invariances inherent to different d...

Please sign up or login with your details

Forgot password? Click here to reset