论文标题
探索深神经网络在对抗防御中的输入和输出层的作用
Exploring the role of Input and Output Layers of a Deep Neural Network in Adversarial Defense
论文作者
论文摘要
深度神经网络正在学习模型，在许多领域都达到了最先进的表现，例如预测，计算机视觉，语言处理等。但是，已经表明存在某些输入不会正常欺骗人类，但可能会完全误导该模型。这些输入称为对抗输入。当在现实世界应用中使用此类模型时，这些输入构成了高度的安全威胁。在这项工作中，我们分析了三种不同类别的完全连接密度网络的阻力，以针对较少测试的非毕业者对抗性攻击。这些类是通过操纵输入和输出层来创建的。我们已经经验证明，由于网络的某些特征，它们可以针对这些攻击提供高度的鲁棒性，并且可以用于微调其他模型以增加对对抗性攻击的防御。
Deep neural networks are learning models having achieved state of the art performance in many fields like prediction, computer vision, language processing and so on. However, it has been shown that certain inputs exist which would not trick a human normally, but may mislead the model completely. These inputs are known as adversarial inputs. These inputs pose a high security threat when such models are used in real world applications. In this work, we have analyzed the resistance of three different classes of fully connected dense networks against the rarely tested non-gradient based adversarial attacks. These classes are created by manipulating the input and output layers. We have proven empirically that owing to certain characteristics of the network, they provide a high robustness against these attacks, and can be used in fine tuning other models to increase defense against adversarial attacks.
