论文标题
隐藏后门后面：反对生成模型的自我碰撞
Hiding Behind Backdoors: Self-Obfuscation Against Generative Models
论文作者
论文摘要
在最近的研究中，已经证明了损害机器学习管道的攻击向量，从扰动到建筑组件。在这项工作的基础上，我们说明了自我碰撞攻击：攻击者针对系统中的预处理模型，并毒化了生成模型的训练集，以使推理期间混淆特定类别。我们的贡献是描述，实施和评估广泛的攻击，以期提高人们对机器学习社区内建筑鲁棒性挑战的认识。
Attack vectors that compromise machine learning pipelines in the physical world have been demonstrated in recent research, from perturbations to architectural components. Building on this work, we illustrate the self-obfuscation attack: attackers target a pre-processing model in the system, and poison the training set of generative models to obfuscate a specific class during inference. Our contribution is to describe, implement and evaluate a generalized attack, in the hope of raising awareness regarding the challenge of architectural robustness within the machine learning community.
