Robust Convolutional Neural Networks under Adversarial Noise
Jonghoon Jin, Aysegul Dundar and Eugenio Culurciello Electrical and Computer Engineering, Purdue University Biomedical Engineering, Purdue University
Abstract
Recent studies have shown that Convolutional Neural Networks (CNNs) are vulnerable to a small perturbation of input called “adversarial examples”. In this work, we propose a new feedforward CNN that improves robustness in the presence of adversarial noise. Our model uses stochastic additive noise added to the input image and to the CNN models. The proposed model operates in conjunction with a CNN trained with either standard or adversarial objective function. In particular, convolution, max-pooling, and ReLU layers are modified to benefit from the noise model. Our feedforward model is parameterized by only a mean and variance per pixel which simplifies computations and makes our method scalable to a deep architecture. From CIFAR-10 and ImageNet test, the proposed model outperforms other methods and the improvement is more evident for difficult classification tasks or stronger adversarial noise.
中文速览
针对卷积神经网络（CNN）容易被对抗样本（adversarial examples）欺骗这一安全隐患，研究者提出了一种随机前馈（stochastic feedforward）CNN框架：在输入图像和网络各层中引入加性高斯噪声，并将每个像素建模为带均值和方差的随机变量，然后推导出卷积、ReLU、最大池化等各层在该随机输入下的解析均值和方差，使不确定性从头到尾贯穿整个网络，而不是仅凭单点预测做判断。整个模型只需为每个像素维护均值和方差两个参数，计算开销小，可扩展到AlexNet这样的深层网络。在CIFAR-10和ImageNet上的实验表明，该方法在对抗噪声存在的情况下始终优于对抗训练等现有方案，任务越难、噪声越强，优势越明显，与标准模型集成后还能将正常配置下的精度损失控制在极小范围内。这项工作为在安全敏感场景中部署更可靠的视觉识别系统提供了一条计算高效、易于落地的路径。
原文 arXiv:1511.06306;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1511.06306v2