arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.07265cs.LGcs.AI
收藏

探索深度度量学习的对抗鲁棒性

Exploring Adversarial Robustness of Deep Metric Learning

Aalborg University(奥尔堡大学);University of Wisconsin-Madison(威斯康星大学麦迪逊分校)

Thomas Kobber Panum, Zi Wang, Pengyu Kan, Earlence Fernandes, Somesh Jha

摘要:

深度度量学习(DML)是一种广泛使用的技术,涉及学习样本对之间的距离度量。DML使用深度神经架构来学习输入的语义嵌入,其中相似示例之间的距离很小,而不同示例之间的距离很远。虽然底层的神经网络在自然发生的样本上产生良好的准确性,但它们容易受到不利扰动样本的影响,从而降低性能。我们朝着训练鲁棒的DML模型迈出了第一步,并解决了度量损失依赖于小批量样本的主要挑战,而不像标准损失只依赖于特定的输入输出对。我们分析了这种依赖效应,并提供了一个强大的优化配方。通过在三个常用的DML数据集上进行实验,我们证明了对抗准确性提高了5-76倍,并且优于现有的DML模型。

英文摘要:

Deep Metric Learning (DML), a widely-used technique, involves learning a distance metric between pairs of samples. DML uses deep neural architectures to learn semantic embeddings of the input, where the distance between similar examples is small while dissimilar ones are far apart. Although the underlying neural networks produce good accuracy on naturally occurring samples, they are vulnerable to adversarially-perturbed samples that reduce performance. We take a first step towards training robust DML models and tackle the primary challenge of the metric losses being dependent on the samples in a mini-batch, unlike standard losses that only depend on the specific input-output pair. We analyze this dependence effect and contribute a robust optimization formulation. Using experiments on three commonly-used DML datasets, we demonstrate 5-76 fold increases in adversarial accuracy, and outperform an existing DML model that sought out to be robust.

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。

↑