论文标题
多种攻击
Manifold attack
论文作者
论文摘要
尤其是机器学习，尤其是在最近的十年中引起了很多兴趣，并且在许多计算机视觉或自然语言处理任务中显示出显着的性能改进。为了处理仅少量培训样本或处理具有大量参数的模型的数据库，正则化是必不可少的。在本文中，我们通过使用“流动攻击”将原始数据的多种保存（多种学习）从原始数据实施到潜在的呈现中。后来以对抗性学习的方式启发：寻找大多数扭曲多种多样保存的虚拟点，然后将这些点用作训练模型的补充样本。我们表明，我们的正则化方法为准确率和对对抗性例子的鲁棒性提供了改进。
Machine Learning in general and Deep Learning in particular has gained much interest in the recent decade and has shown significant performance improvements for many Computer Vision or Natural Language Processing tasks. In order to deal with databases which have just a small amount of training samples or to deal with models which have large amount of parameters, the regularization is indispensable. In this paper, we enforce the manifold preservation (manifold learning) from the original data into latent presentation by using "manifold attack". The later is inspired in a fashion of adversarial learning : finding virtual points that distort mostly the manifold preservation then using these points as supplementary samples to train the model. We show that our approach of regularization provides improvements for the accuracy rate and for the robustness to adversarial examples.
