Defending Against Backdoor Attack on Graph Nerual Network by Explainability

09/07/2022
by   Bingchen Jiang, et al.
0

Backdoor attack is a powerful attack algorithm to deep learning model. Recently, GNN's vulnerability to backdoor attack has been proved especially on graph classification task. In this paper, we propose the first backdoor detection and defense method on GNN. Most backdoor attack depends on injecting small but influential trigger to the clean sample. For graph data, current backdoor attack focus on manipulating the graph structure to inject the trigger. We find that there are apparent differences between benign samples and malicious samples in some explanatory evaluation metrics, such as fidelity and infidelity. After identifying the malicious sample, the explainability of the GNN model can help us capture the most significant subgraph which is probably the trigger in a trojan graph. We use various dataset and different attack settings to prove the effectiveness of our defense method. The attack success rate all turns out to decrease considerably.

READ FULL TEXT
research
06/19/2020

Backdoor Attacks to Graph Neural Networks

Node classification and graph classification are two basic graph analyti...
research
10/25/2022

Motif-Backdoor: Rethinking the Backdoor Attack on Graph Neural Networks via Motifs

Graph neural network (GNN) with a powerful representation capability has...
research
12/31/2020

Explainability in Graph Neural Networks: A Taxonomic Survey

Deep learning methods are achieving ever-increasing performance on many ...
research
03/25/2021

Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation

Prior works on formalizing explanations of a graph neural network (GNN) ...
research
07/26/2022

ScoreCAM GNN: une explication optimale des réseaux profonds sur graphes

The explainability of deep networks is becoming a central issue in the d...
research
08/08/2023

XGBD: Explanation-Guided Graph Backdoor Detection

Backdoor attacks pose a significant security risk to graph learning mode...
research
04/10/2021

A Low-Cost Attack against the hCaptcha System

CAPTCHAs are a defense mechanism to prevent malicious bot programs from ...

Please sign up or login with your details

Forgot password? Click here to reset