Tabdoor: Backdoor Vulnerabilities in Transformer-based Neural Networks for Tabular Data

arXiv:2311.07550v3 Announce Type: replace
Abstract: Deep Neural Networks (DNNs) have shown great promise in various domains. Alongside these developments, vulnerabilities associated with DNN training, such as backdoor attacks, are a significant concern. These attacks involve the subtle insertion of triggers during model training, allowing for manipulated predictions. More recently, DNNs for tabular data have gained increasing attention due to the rise of transformer models. Our research presents a comprehensive analysis of backdoor attacks on tabular data using DNNs, mainly focusing …

arxiv attacks backdoor backdoor attacks cs.cr cs.lg data domains great model training networks neural networks predictions training vulnerabilities