Do more with less: Architecture-agnostic and data-free extraction attack against tabular model

In recent years, numerous model extraction attacks have been proposed to investigate the potential vulnerabilities of tabular models. However, applying these attacks in real-world scenarios remains challenging, as most require access to the victim model's original training data samples or knowledge of its architecture, which is often hard to acquire. To fill this gap, we propose TabExtractor, a novel architecture-agnostic tabular model extraction approach that can be conducted in the data-free setup. Specifically, it includes a new tabular generator that synthesizes informative tabular samples to eliminate the need for the victim model's original training data samples. Meanwhile, we propose a new contrastive tabular transformer (CTT) as the backbone architecture for the clone model to handle the challenges posed by unknown victim model architectures. During the extraction process, we develop three loss functions to strengthen the synthesis quality of the tabular generator and introduce a joint loss function to help the CTT establish well-defined decision boundaries. Extensive experiments on six victim architectures across four real-world datasets demonstrate the effectiveness of TabExtractor. Notably, the clone model extracted by TabExtractor can achieve a 92-100% accuracy of the victim. Our study highlights the potential security risks of tabular models and provides valuable insights into developing robust protection schemes.