We evaluated adversarial robustness with CAA, an ensemble of gradient and search attacks which was recently demonstrated as the most effective attack against a tabular model.

Traditional Anomaly Detection (AD) methods have predominantly relied on unsupervised learning from extensive normal data.

Which transformer scaling regimes are able to perfectly solve different classes of algorithmic problems?

Equally contribute to this research.

The meta generator is termed as MGDD in our approach. Once adapted, it can handle arbitrary sizes of synthetic datasets, even for those unseen during adaptation.