Deep generative models as an adversarial attack strategy for tabular machine learning
This work addresses adversarial robustness for tabular ML systems, which is an incremental extension of techniques from computer vision.
The paper tackled the problem of generating realistic adversarial examples for tabular machine learning by adapting deep generative models, and it evaluated their effectiveness in preserving domain constraints.
Deep Generative Models (DGMs) have found application in computer vision for generating adversarial examples to test the robustness of machine learning (ML) systems. Extending these adversarial techniques to tabular ML presents unique challenges due to the distinct nature of tabular data and the necessity to preserve domain constraints in adversarial examples. In this paper, we adapt four popular tabular DGMs into adversarial DGMs (AdvDGMs) and evaluate their effectiveness in generating realistic adversarial examples that conform to domain constraints.