跳到主要导航 跳到搜索 跳到主要内容

Backdoor Training Paradigm in Generative Adversarial Networks

  • Huangji Wang
  • , Fan Cheng*
  • *此作品的通讯作者
  • Shanghai Jiao Tong University

科研成果: 期刊稿件 › 文章 › 同行评审

摘要

Backdoor attacks remain a critical area of focus in machine learning research, with one prominent approach being the introduction of backdoor training injection mechanisms. These mechanisms embed backdoor triggers into the training process, enabling the model to recognize specific trigger inputs and produce predefined outputs post-training. In this paper, we identify a unifying pattern across existing backdoor injection methods in generative models and propose a novel backdoor training injection paradigm. This paradigm leverages a unified loss function design to facilitate backdoor injection across diverse generative models. We demonstrate the effectiveness and generalizability of this paradigm through experiments on generative adversarial networks (GANs) and Diffusion Models. Our experimental results on GANs confirm that the proposed method successfully embeds backdoor triggers, enhancing the model’s security and robustness. This work provides a new perspective and methodological framework for backdoor injection in generative models, making a significant contribution toward improving the safety and reliability of these models.

源语言英语
期刊论文编号283
期刊Entropy
卷27
期3
DOI
出版状态已出版 - 3月 2025
已对外发布是

学术指纹

探究 'Backdoor Training Paradigm in Generative Adversarial Networks' 的科研主题。它们共同构成独一无二的学术指纹。

引用此