Finding MNEMON: Reviving Memories of Node Embeddings - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Finding MNEMON: Reviving Memories of Node Embeddings

Résumé

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.

Dates et versions

hal-03893484 , version 1 (11-12-2022)

Identifiants

Citer

Yun Shen, Yufei Han, Zhikun Zhang, Min Chen, Ting Yu, et al.. Finding MNEMON: Reviving Memories of Node Embeddings. CCS 2022 - ACM SIGSAC Conference on Computer and Communications Security, Nov 2022, Los Angeles CA, United States. pp.2643-2657, ⟨10.1145/3548606.3559358⟩. ⟨hal-03893484⟩
38 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More