arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2102.09701cs.LG
收藏

中心平滑:结构化输出网络的认证鲁棒性

Center Smoothing: Certified Robustness for Networks with Structured Outputs

University of Maryland(马里兰大学)

Aounon Kumar, Tom Goldstein

摘要:

可证明对抗鲁棒性的研究主要限于分类任务和具有一维实值输出的模型。我们将可证明的鲁棒性的范围扩展到具有更一般和结构化输出的问题,如集合,图像,语言等。我们将输出空间建模为距离/相似性函数下的度量空间,如交集,感知相似性,总变化距离等。此类模型用于许多机器学习问题,如图像分割,目标检测,生成模型,图像/音频到文本系统等。基于称为随机平滑的鲁棒性技术,我们的$\textit{center smoothing}$过程可以产生保证输出中的变化的模型,如通过距离度量测量的,对于输入的任何范数有界的对抗性扰动保持较小。我们应用我们的方法来创建具有不同输出空间的可证明的鲁棒模型-从集合到图像-并表明它产生有意义的证书,而不会显着降低基础模型的性能。我们的实验代码可在https://github.com/aounon/center-smoothing上获得。

英文摘要:

The study of provable adversarial robustness has mostly been limited to classification tasks and models with one-dimensional real-valued outputs. We extend the scope of certifiable robustness to problems with more general and structured outputs like sets, images, language, etc. We model the output space as a metric space under a distance/similarity function, such as intersection-over-union, perceptual similarity, total variation distance, etc. Such models are used in many machine learning problems like image segmentation, object detection, generative models, image/audio-to-text systems, etc. Based on a robustness technique called randomized smoothing, our $\textit{center smoothing}$ procedure can produce models with the guarantee that the change in the output, as measured by the distance metric, remains small for any norm-bounded adversarial perturbation of the input. We apply our method to create certifiably robust models with disparate output spaces - from sets to images - and show that it yields meaningful certificates without significantly degrading the performance of the base model. Code for our experiments is available at: https://github.com/aounon/center-smoothing.

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。

↑