aiqbench analysis
PriDyG addresses the critical challenge of accumulating privacy loss in dynamic graph learning by combining GNN structural updates with LLM semantic reasoning under differential privacy constraints. The framework's incremental aggregation technique ensures total privacy costs remain constant regardless of update frequency, significantly outperforming geometrically decaying baselines while preserving high utility for node classification and link prediction tasks. This work represents a significant advancement in securing machine learning pipelines that process evolving relational data without compromising sensitive edge information.
PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration
arXiv:2608.04255v1 Announce Type: cross Abstract: Graph inference over relational data can expose sensitive edge information, and this risk becomes more severe in dynamic graphs, where repeated model updates cause privacy loss to accumulate. We formulate Edge-level Differentially Private Dynamic Graph Inference (EDG) and propose PriDyG, a private inference framework that combines GNN-based structural learning with LLM-based semantic reasoning. PriDyG introduces incremental private multi-hop aggregation, which buffers newly arrived edges and processes each edge exactly once. By parallel composition, the total privacy cost equals that of a single static release, independent of the number or schedule of model updates. Compared with geometrically decaying budget allocation, incremental aggregation avoids exponentially increasing noise while preserving exact one-hop signals and at least half of two-hop information transfers. PriDyG further complements privatized GNN outputs with LLM predictions derived solely from node text, incurring no additional edge-level privacy cost. Experiments on four benchmarks for node classification and link prediction show that PriDyG consistently outperforms geometrically decaying baselines under the same privacy budget and matches the utility of naive per-update retraining while reducing cumulative privacy cost by up to three orders of magnitude.
Abstract:Graph inference over relational data can expose sensitive edge information, and this risk becomes more severe in dynamic graphs, where repeated model updates cause privacy loss to accumulate. We formulate Edge-level Differentially Private Dynamic Graph Inference (EDG) and propose PriDyG, a private inference framework that combines GNN-based structural learning with LLM-based semantic reasoning. PriDyG introduces incremental private multi-hop aggregation, which buffers newly arrived edges and processes each edge exactly once. By parallel composition, the total privacy cost equals that of a single static release, independent of the number or schedule of model updates. Compared with geometrically decaying budget allocation, incremental aggregation avoids exponentially increasing noise while preserving exact one-hop signals and at least half of two-hop information transfers. PriDyG further complements privatized GNN outputs with LLM predictions derived solely from node text, incurring no additional edge-level privacy cost. Experiments on four benchmarks for node classification and link prediction show that PriDyG consistently outperforms geometrically decaying baselines under the same privacy budget and matches the utility of naive per-update retraining while reducing cumulative privacy cost by up to three orders of magnitude.
Cryptography and Security (cs.CR); Machine Learning (cs.LG)
arXiv:2608.04255 [cs.CR]
(or arXiv:2608.04255v1 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2608.04255 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 279 words
Related coverage
[AINews] Muse Spark 1.3 matches GPT-5.6-Sol, confirming Meta Superintelligence as the newest Frontier Lab, >90% discount for training
Latent Space · Sep 3, 2026
TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning
arXiv · Jul 21, 2026
Edge Sparsification via Temporal Forman-Ricci Curvature for Dynamic Graph Learning
arXiv · Aug 25, 2026
SonicSampler: Unified Tile-Aware Kernels for LLM Sampling and Speculative Verification
arXiv · Jul 25, 2026