cd /news/machine-learning/oblivdgl-oblivious-deep-graph-learni… · home › topics › machine-learning › article
[ARTICLE · art-168975] src=eprint.iacr.org ↗ pub= topic=machine-learning verified=true sentiment=↑ positive

OblivDGL: Oblivious Deep Graph Learning Made Practical

Researchers designed and implemented OblivDGL, an oblivious deep graph learning framework for secure graph neural network (GNN) inference and training, built on a new oblivious message passing paradigm and an oblivious graph representation realized with function secret sharing (FSS). Evaluated on four benchmark graph datasets, OblivDGL reduced communication cost by up to 1024x and achieved up to 14.3x runtime speedup during secure training versus state-of-the-art secure GNN frameworks, and delivered up to 754x lower communication and a 4.19x speedup for secure inference. The framework leaks no private information except the total number of edges and nodes, addressing prior designs that could not simultaneously achieve security, functionality and scalability on large graphs.

key takeaway

OblivDGL's FSS-based oblivious message passing cuts secure GNN training communication by up to 1024x with a 14.3x runtime speedup, and secure inference communication by up to 754x with a 4.19x speedup, while revealing only the total edge and node counts.

by read1 min views15 publishedOct 27, 2026

The rapid deployment of Graph Neural Networks (GNNs) within Machine Learning as a Service (MLaaS) has opened up new privacy concerns. Both sensitive graph data and proprietary GNN models are submitted to and processed in third-party MLaaS platform for training and inference. To alleviate those concerns, recent efforts have been made to design tailored secure computation protocols for GNNs. Unfortunately, existing designs cannot accomplish security, functionality, and scalability simultaneously. They leak a certain degree of graph information, offer limited support on secure training of GNNs, and can hardly scale to large graphs. In this paper, we design and implement OblivDGL, an oblivious deep graph learning framework for secure GNN inference and training. Our design is inspired by Deep Graph Library (DGL), an industrial practice for graph learning. At its core, we distill the secure computational patterns of GNNs into a generalized form, and empower both secure GNN training and inference through a novel oblivious message passing paradigm. To realize such a paradigm, we design a new oblivious graph representation, and realize it by function secret sharing (FSS), a lightweight secure computation technique with low latency. Compared to prior secure GNN systems, OblivDGL achieves the most stringent privacy guarantees, i.e., revealing no private information except for the total number of edges and nodes. One standout feature of OblivDGL is the scalability of processing encrypted graphs by carefully tailored parallelization designs. Extensive evaluations on four benchmark graph datasets demonstrate that, compared to state-of-the-art secure GNN frameworks, OblivDGL reduces communication cost by up to 1024x and achieves up to 14.3x speedup in runtime during secure training. For secure inference, OblivDGL achieves up to 754x lower communication and a 4.19x speedup.

── more in #machine-learning 4 stories · sorted by recency
── more on @oblivdgl 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/oblivdgl-oblivious-d…] indexed:0 read:1min 2026-10-27 · —