SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1910.14356 · 2019

Certifiable Robustness to Graph Perturbations

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
abojchevski/graph_cert canonical 0 of 2
FunctionStatusWhere it lives
policy_iteration Not yet run abojchevski/graph_cert/graph_cert/certify.py
code served (permissive licence) · get_code("3438a101fa992299")
upper_bounds_max_ppr_target Not yet run abojchevski/graph_cert/graph_cert/certify.py
code served (permissive licence) · get_code("b7c3c82aff6faf0a")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Despite the exploding interest in graph neural networks there has been little effort to verify and improve their robustness. This is even more alarming given recent findings showing that they are extremely vulnerable to adversarial attacks on both the graph structure and the node attributes. We propose the first method for verifying certifiable (non-)robustness to graph perturbations for a general class of models that includes graph neural networks and label/feature propagation. By exploiting connections to PageRank and Markov decision processes our certificates can be efficiently (and under many threat models exactly) computed. Furthermore, we investigate robust training procedures that increase the number of certifiably robust nodes while maintaining or improving the clean predictive accuracy.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1910.14356")
get_code_for_paper("1910.14356")
have("1910.14356")

Connect an agent — have() is free.