REVIEW 5 cited by
SoK: Differential Privacy on Graph-Structured Data
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In this work, we study the applications of differential privacy (DP) in the context of graph-structured data. We discuss the formulations of DP applicable to the publication of graphs and their associated statistics as well as machine learning on graph-based data, including graph neural networks (GNNs). The formulation of DP in the context of graph-structured data is difficult, as individual data points are interconnected (often non-linearly or sparsely). This connectivity complicates the computation of individual privacy loss in differentially private learning. The problem is exacerbated by an absence of a single, well-established formulation of DP in graph settings. This issue extends to the domain of GNNs, rendering private machine learning on graph-structured data a challenging task. A lack of prior systematisation work motivated us to study graph-based learning from a privacy perspective. In this work, we systematise different formulations of DP on graphs, discuss challenges and promising applications, including the GNN domain. We compare and separate works into graph analysis tasks and graph learning tasks with GNNs. Finally, we conclude our work with a discussion of open questions and potential directions for further research in this area.
Forward citations
Cited by 5 Pith papers
-
PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration
Introduces incremental private multi-hop aggregation so that edge-level differential privacy cost stays constant across arbitrarily many updates to a dynamic graph, plus an LLM branch that adds utility at no extra pri...
-
SoK: Practical Aspects of Releasing Differentially Private Graphs
The authors provide a systematization of differentially private graph release methods along with an objective-based framework and two illustrative evaluations for social network analysts.
-
Practical and Accurate Local Edge Differentially Private Graph Algorithms
New LEDP k-core and triangle-counting algorithms replace edge-count error bounds with degree- and degeneracy-based bounds, and are evaluated in a distributed simulation with reported accuracy improvements.
-
EdgeRefine: Privacy-Utility Balance for Graphs via Jaccard Sampling under Edge Differential Privacy
EdgeRefine denoises randomized-response graphs by ranking edges with Jaccard similarity and sampling a fixed quota from observed and non-observed edges, reporting near-noise-free GNN accuracy under edge differential privacy.
-
Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses
A systematic review that organizes graph-ML IP protection into model-level and data-level attacks and defenses, and ships a benchmark library, PyGIP.
Discussion (0). Continue with ORCID to comment.