mlsanityData to 7 Oct 2026

Adversarial Attacks on Locally Private Graph Neural Networks

arXiv 2603.20746 ↗First posted 21 Mar 2026cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph neural network (GNN) is a powerful tool for analyzing graph-structured data. However, their vulnerability to adversarial attacks raises serious concerns, especially when dealing with sensitive information. Local Differential Privacy (LDP) offers a privacy-preserving framework for training GNNs, but its impact on adversarial robustness remains underexplored. This paper investigates adversarial attacks on LDP-protected GNNs. We explore how the privacy guarantees of LDP can be leveraged or hindered by adversarial perturbations. The effectiveness of existing attack methods on LDP-protected GNNs are analyzed and potential challenges in crafting adversarial examples under LDP constraints are discussed. Additionally, we suggest directions for defending LDP-protected GNNs against adversarial attacks. This work investigates the interplay between privacy and security in graph learning, highlighting the need for robust and privacy-preserving GNN architectures.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 38 references that are in the map. First posted on arXiv 21 Mar 2026.

Builds on

21 of 38 references.

References · 21

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  4. 2014RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Responsecited by 262
  5. 2020Towards More Practical Adversarial Attacks on Graph Neural Networkscited by 76
  6. 2021TDGIA:Effective Injection Attacks on Graph Neural Networkscited by 67
  7. 2020Locally Private Graph Neural Networkscited by 64
  8. 2021Single Node Injection Attack against Graph Neural Networkscited by 45
  9. 2021Releasing Graph Neural Networks with Differential Privacy Guaranteescited by 32
  10. 2022Model Inversion Attacks against Graph Neural Networkscited by 26
  11. 2023A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applicationscited by 22
  12. 2021Adversarial Attack on Graph Neural Networks as An Influence Maximization Problemcited by 20
9 more
  1. 2022Private Graph Extraction via Feature Explanationscited by 16
  2. 2021NetFense: Adversarial Defenses against Privacy Attacks on Neural Networks for Graph Datacited by 13
  3. 2022Differentially Private Graph Classification with GNNscited by 12
  4. 2023ProGAP: Progressive Graph Neural Networks with Differential Privacy Guaranteescited by 12
  5. 2023Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protectioncited by 12
  6. 2022SecGNN: Privacy-Preserving Graph Neural Network Training and Inference as a Cloud Servicecited by 10
  7. 2022GANI: Global Attacks on Graph Neural Networks via Imperceptible Node Injectionscited by 10
  8. 2023Training Differentially Private Graph Neural Networks with Random Walk Samplingcited by 5
  9. 2023Local Differential Privacy in Graph Neural Networks: a Reconstruction Approachcited by 5

Built on by

Not cited yet.