Timezone: »

Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More
Aleksandar Bojchevski · Johannes Klicpera · Stephan Günnemann

Thu Jul 16 12:00 PM -- 12:45 PM & Fri Jul 17 01:00 AM -- 01:45 AM (PDT) @ None #None

Existing techniques for certifying the robustness of models for discrete data either work only for a small class of models or are general at the expense of efficiency or tightness. Moreover, they do not account for sparsity in the input which, as our findings show, is often essential for obtaining non-trivial guarantees. We propose a model-agnostic certificate based on the randomized smoothing framework which subsumes earlier work and is tight, efficient, and sparsity-aware. Its computational complexity does not depend on the number of discrete categories or the dimension of the input (e.g. the graph size), making it highly scalable. We show the effectiveness of our approach on a wide variety of models, datasets, and tasks -- specifically highlighting its use for Graph Neural Networks. So far, obtaining provable guarantees for GNNs has been difficult due to the discrete and non-i.i.d. nature of graph data. Our method can certify any GNN and handles perturbations to both the graph structure and the node attributes.

Author Information

Aleksandar Bojchevski (Technical University of Munich)
Johannes Klicpera (Technical University Munich)
Stephan Günnemann (Technical University of Munich)

More from the Same Authors