基于酉梯度神经网络的鲁棒设计分类
Robust-by-Design Classification via Unitary-Gradient Neural Networks
摘要：
由于存在对抗攻击，在安全关键系统中使用神经网络需要安全和鲁棒的模型。知道任何输入x的最小对抗扰动，或者等价地，知道x与分类边界的距离，允许评估分类鲁棒性，提供可验证的预测。不幸的是，用于计算这种距离的现有技术在计算上是昂贵的，因此不适合在线应用。这项工作提出了一种新的分类器家族，即符号距离分类器（SDC），从理论角度来看，直接输出x与分类边界的精确距离，而不是概率得分（例如，SoftMax）。SDC代表了一系列鲁棒设计分类器。为了实际解决SDC的理论要求，提出了一种新的网络结构，称为酉梯度神经网络。实验结果表明，所提出的架构近似于一个有符号的距离分类器，因此允许一个在线的可证明的分类x的成本一个单一的推理。
英文摘要：
The use of neural networks in safety-critical systems requires safe and robust models, due to the existence of adversarial attacks. Knowing the minimal adversarial perturbation of any input x, or, equivalently, knowing the distance of x from the classification boundary, allows evaluating the classification robustness, providing certifiable predictions. Unfortunately, state-of-the-art techniques for computing such a distance are computationally expensive and hence not suited for online applications. This work proposes a novel family of classifiers, namely Signed Distance Classifiers (SDCs), that, from a theoretical perspective, directly output the exact distance of x from the classification boundary, rather than a probability score (e.g., SoftMax). SDCs represent a family of robust-by-design classifiers. To practically address the theoretical requirements of a SDC, a novel network architecture named Unitary-Gradient Neural Network is presented. Experimental results show that the proposed architecture approximates a signed distance classifier, hence allowing an online certifiable classification of x at the cost of a single inference.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
