SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.06663 · 2021

TDGIA:Effective Injection Attacks on Graph Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

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

Abstract

Graph Neural Networks (GNNs) have achieved promising performance in various real-world applications. However, recent studies have shown that GNNs are vulnerable to adversarial attacks. In this paper, we study a recently-introduced realistic attack scenario on graphs -- graph injection attack (GIA). In the GIA scenario, the adversary is not able to modify the existing link structure and node attributes of the input graph, instead the attack is performed by injecting adversarial nodes into it. We present an analysis on the topological vulnerability of GNNs under GIA setting, based on which we propose the Topological Defective Graph Injection Attack (TDGIA) for effective injection attacks. TDGIA first introduces the topological defective edge selection strategy to choose the original nodes for connecting with the injected ones. It then designs the smooth feature optimization objective to generate the features for the injected nodes. Extensive experiments on large-scale datasets show that TDGIA can consistently and significantly outperform various attack baselines in attacking dozens of defense GNN models. Notably, the performance drop on target GNNs resultant from TDGIA is more than double the damage brought by the best attack solution among hundreds of submissions on KDD-CUP 2020.

For agents

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

get_harvested_code_for_paper("2106.06663")
get_code_for_paper("2106.06663")
have("2106.06663")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2106.06663.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2106.06663.svg)](https://syntology.ai/paper/2106.06663)

Connect an agent — have() is free.