The rise of pre-trained unified foundation models breaks down the barriers between different modalities and tasks, providing comprehensive support to users with unified architectures. However, the backdoor attack on pre-trained models poses a serious threat to their security. Previous research on backdoor attacks has been limited to uni-modal tasks or single tasks across modalities, making it inapplicable to unified foundation models. In this paper, we make proof-of-concept level research on the backdoor attack for pre-trained unified foundation models. Through preliminary experiments on NLP and CV classification tasks, we reveal the vulnerability of these models and suggest future research directions for enhancing the attack approach.
翻译:培训前统一基础模型的兴起打破了不同模式和任务之间的障碍,为拥有统一架构的用户提供了全面支持;然而,对培训前模式的后门攻击对其安全构成严重威胁。以前关于后门攻击的研究仅限于单式任务或各种模式的单一任务,使其不适用于统一基础模型。在本文件中,我们对培训前统一基础模型的后门攻击进行概念层面研究证明。通过对NLP和CV分类任务的初步实验,我们揭示了这些模式的脆弱性,并提出了加强攻击方法的未来研究方向。</s>