Adversarial examples are perturbed inputs which can cause a serious threat
for machine learning models. Finding these perturbations is such a hard task
that we can only use the iterative methods to traverse. For computational
efficiency, recent works use adversarial generative networks to model the
distribution of both the universal or image-dependent perturbations directly.
However, these methods generate perturbations only rely on input images. In
this work, we propose a more general-purpose framework which infers
target-conditioned perturbations dependent on both input image and target
label. Different from previous single-target attack models, our model can
conduct target-conditioned attacks by learning the relations of attack target
and the semantics in image. Using extensive experiments on the datasets of
MNIST and CIFAR10, we show that our method achieves superior performance with
single target attack models and obtains high fooling rates with small
perturbation norms.

提出一种更通用的框架，该框架可以推断基于输入图像和目标标签的目标条件扰动，通过学习攻击目标与图像中的语义关系。在 MNIST 和 CIFAR10 数据集的广泛实验中，该方法实现了超越单目标攻击模型的优异性能，并以小扰动范数获得高愚弄率。