Robustness of Graph Neural Networks at Scale
Graph Neural Networks (GNNs) are increasingly important given their popularity and the diversity of applications. Yet, existing studies of their vulnerability to adversarial attacks rely on relatively small graphs. We address this gap and study how to attack and defend GNNs at scale. We propose two sparsity-aware first-order optimization attacks that maintain an efficient representation despite optimizing over a number of parameters which is quadratic in the number of nodes. We show that common surrogate losses are not well-suited for global attacks on GNNs. Our alternatives can double the attack strength. Moreover, to improve GNNs' reliability we design a robust aggregation function, Soft Median, resulting in an effective defense at all scales. We evaluate our attacks and defense with standard GNNs on graphs more than 100 times larger compared to previous work. We even scale one order of magnitude further by extending our techniques to a scalable GNN.
Code (2)
Tasks
DiversitySimilar Papers 제목 키워드 기반
Loop Shaping with Scaled Relative Graphs
The Scaled Relative Graph (SRG) is a generalization of the Nyquist diagram that may be plotted for nonlinear operators, and allows nonlinear robustness margins to be defined graphically. This abstract explores techniques…
GeoNet: Benchmarking Unsupervised Adaptation across Geographies
In recent years, several efforts have been aimed at improving the robustness of vision models to domains and environments unseen during training. An important practical problem pertains to models deployed in a new geogra…
BenchmarkingDomain Adaptationimage-classificationImage Classification+2Zero Shot Learning via Multi-Scale Manifold Regularization
We address zero-shot learning using a new manifold alignment framework based on a localized multi-scale transform on graphs. Our inference approach includes a smoothness criterion for a function mapping nodes on a graph …
Zero-Shot LearningHigh-fidelity lunar topographic reconstruction across diverse terrain and illumination environments using deep learning
Topographic models are essential for characterizing planetary surfaces and for inferring underlying geological processes. Nevertheless, meter-scale topographic data remain limited, which constrains detailed planetary inv…
On the Robustness of Graph Reduction Against GNN Backdoor
Graph Neural Networks (GNNs) are gaining popularity across various domains due to their effectiveness in learning graph-structured data. Nevertheless, they have been shown to be susceptible to backdoor poisoning attacks,…
Computational EfficiencyData Poisoning