arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.02532cs.LG
收藏

将对抗训练作为后处理步骤的自动化鲁棒性

Automated Robustness with Adversarial Training as a Post-Processing Step

IBM Research Europe(IBM欧洲研究院);IBM Technology Campus, Damastown Ind. Park(IBM科技园区,达马斯敦工业园区)

Ambrish Rawat, Mathieu Sinn, Beat Buesser

摘要:

对抗性训练是一项计算代价高昂的任务,因此寻找以鲁棒性为标准的神经网络架构可能具有挑战性。作为迈向实用自动化的一步,这项工作探索了一个简单的后处理步骤在产生强大的深度学习模型方面的功效。为了实现这一目标,我们采用对抗训练作为从神经架构搜索算法获得的优化网络架构的后处理步骤。采用特定的策略来调整不同步骤的超参数,从而产生用于生成对抗性鲁棒的深度学习模型的全自动管道。我们证明了建议的管道的有用性,在11个图像分类和9个文本分类任务进行了广泛的实验。

英文摘要:

Adversarial training is a computationally expensive task and hence searching for neural network architectures with robustness as the criterion can be challenging. As a step towards practical automation, this work explores the efficacy of a simple post processing step in yielding robust deep learning model. To achieve this, we adopt adversarial training as a post-processing step for optimised network architectures obtained from a neural architecture search algorithm. Specific policies are adopted for tuning the hyperparameters of the different steps, resulting in a fully automated pipeline for generating adversarially robust deep learning models. We evidence the usefulness of the proposed pipeline with extensive experimentation across 11 image classification and 9 text classification tasks.

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。

↑