(2022) Finding MNEMON: Reviving Memories of Node Embeddings.
|
Text
2204.06963.pdf Download (25MB) | Preview |
Abstract
Previous security research efforts orbiting around graphs have been exclusively focusing on either (de-)anonymizing the graphs or understanding the security and privacy issues of graph neural networks. Little attention has been paid to understand the privacy risks of integrating the output from graph embedding models (e.g., node embeddings) with complex downstream machine learning pipelines. In this paper, we fill this gap and propose a novel model-agnostic graph recovery attack that exploits the implicit graph structural information preserved in the embeddings of graph nodes. We show that an adversary can recover edges with decent accuracy by only gaining access to the node embedding matrix of the original graph without interactions with the node embedding models. We demonstrate the effectiveness and applicability of our graph recovery attack through extensive experiments.
| Item Type: | Conference or Workshop Item (A Paper) (Paper) |
|---|---|
| Divisions: | Michael Backes (InfSec) Yang Zhang (YZ) |
| Conference: | CCS ACM Conference on Computer and Communications Security |
| Depositing User: | Min Chen |
| Date Deposited: | 25 Apr 2022 09:26 |
| Last Modified: | 25 Apr 2022 09:26 |
| Primary Research Area: | NRA1: Trustworthy Information Processing |
| URI: | https://publications.cispa.saarland/id/eprint/3620 |
Actions
Actions (login required)
 |
View Item |