# Information Obfuscation of Graph Neural Networks

arXiv: https://arxiv.org/abs/2009.13504 · HTML: https://mlsanity.com/paper/2009.13504/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2020.

## Built on by (most cited first, 19 of 19)

- [A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability](https://mlsanity.com/paper/2204.08570/) (2022)
- [Trustworthy Graph Neural Networks: Aspects, Methods and Trends](https://mlsanity.com/paper/2205.07424/) (2022)
- [A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challenges](https://mlsanity.com/paper/2403.04468/) (2024)
- [GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation](https://mlsanity.com/paper/2203.00949/) (2022)
- [A Comprehensive Survey on Trustworthy Recommender Systems](https://mlsanity.com/paper/2209.10117/) (2022)
- [Pairwise Alignment Improves Graph Domain Adaptation](https://mlsanity.com/paper/2403.01092/) (2024)
- [A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications](https://mlsanity.com/paper/2308.16375/) (2023)
- [Differentially Private Graph Classification with GNNs](https://mlsanity.com/paper/2202.02575/) (2022)
- [Use of Graph Neural Networks in Aiding Defensive Cyber Operations](https://mlsanity.com/paper/2401.05680/) (2024)
- [Gromov-Wasserstein Discrepancy with Local Differential Privacy for Distributed Structural Graphs](https://mlsanity.com/paper/2202.00808/) (2022)
- [Privacy and Transparency in Graph Machine Learning: A Unified Perspective](https://mlsanity.com/paper/2207.10896/) (2022)
- [Learning Robust and Privacy-Preserving Representations via Information Theory](https://mlsanity.com/paper/2412.11066/) (2024)
- [Privacy-Preserved Neural Graph Similarity Learning](https://mlsanity.com/paper/2210.11730/) (2022)
- [Structural Alignment Improves Graph Test-Time Adaptation](https://mlsanity.com/paper/2502.18334/) (2025)
- [Large-Scale Privacy-Preserving Network Embedding against Private Link Inference Attacks](https://mlsanity.com/paper/2205.14440/) (2022)
- [Every Node Counts: Improving the Training of Graph Neural Networks on Node Classification](https://mlsanity.com/paper/2211.16631/) (2022)
- [Promoting Fairness in GNNs: A Characterization of Stability](https://mlsanity.com/paper/2309.03648/) (2023)
- [Towards Anonymous Neural Network Inference](https://mlsanity.com/paper/2505.18398/) (2025)
- [Generative Artificial Intelligence for Literature Reviews](https://mlsanity.com/paper/2605.16475/) (2026)

## Abstract (arXiv)

While the advent of Graph Neural Networks (GNNs) has greatly improved node and graph representation learning in many applications, the neighborhood aggregation scheme exposes additional vulnerabilities to adversaries seeking to extract node-level information about sensitive attributes. In this paper, we study the problem of protecting sensitive attributes by information obfuscation when learning with graph structured data. We propose a framework to locally filter out pre-determined sensitive attributes via adversarial training with the total variation and the Wasserstein distance. Our method creates a strong defense against inference attacks, while only suffering small loss in task performance. Theoretically, we analyze the effectiveness of our framework against a worst-case adversary, and characterize an inherent trade-off between maximizing predictive accuracy and minimizing information leakage. Experiments across multiple datasets from recommender systems, knowledge graphs and quantum chemistry demonstrate that the proposed approach provides a robust defense across various graph structures and tasks, while producing competitive GNN encoders for downstream tasks.