Pith. sign in

REVIEW

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2008.12952 v2 pith:VE62JVUG submitted 2020-08-29 cs.LG cs.CRcs.SIstat.ML

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

classification cs.LG cs.CRcs.SIstat.ML
keywords discretegraphdatamodelsefficientguaranteesinputobtaining
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.