Exact Verification of Graph Neural Networks with Incremental Constraint Solving
By: Minghao Liu, Chia-Hsuan Lu, Marta Kwiatkowska
Potential Business Impact:
Protects smart computer networks from being tricked.
Graph neural networks (GNNs) are increasingly employed in high-stakes applications, such as fraud detection or healthcare, but are susceptible to adversarial attacks. A number of techniques have been proposed to provide adversarial robustness guarantees, but support for commonly used aggregation functions in message-passing GNNs is still lacking. In this paper, we develop an exact (sound and complete) verification method for GNNs to compute guarantees against attribute and structural perturbations that involve edge addition or deletion, subject to budget constraints. Focusing on node classification tasks, our method employs constraint solving with bound tightening, and iteratively solves a sequence of relaxed constraint satisfaction problems while relying on incremental solving capabilities of solvers to improve efficiency. We implement GNNev, a versatile solver for message-passing neural networks, which supports three aggregation functions, sum, max and mean, with the latter two considered here for the first time. Extensive experimental evaluation of GNNev on two standard benchmarks (Cora and CiteSeer) and two real-world fraud datasets (Amazon and Yelp) demonstrates its usability and effectiveness, as well as superior performance compared to existing {exact verification} tools on sum-aggregated node classification tasks.
Similar Papers
Robustness Verification of Graph Neural Networks Via Lightweight Satisfiability Testing
Machine Learning (CS)
Finds fake changes in computer networks.
Why does your graph neural network fail on some graphs? Insights from exact generalisation error
Machine Learning (Stat)
Explains why computer "brains" learn from connected data.
Automated discovery of finite volume schemes using Graph Neural Networks
Machine Learning (CS)
Computers invent new math for science problems.