Evaluating the Robustness of Deep-learning Algorithm-selection Models by Evolving Adversarial Instances - Code and Data

This repository contains the code and data for reproducibility of the paper 'Evaluating the Robustness of Deep-learning Algorithm-selection Models by Evolving Adversarial Instances'. The following files are included: Data.zip : contains the original instances in the datasets; Models.zip : trained Deep Neural Networks models used in the paper; New_instances.zip : generated instances using the approach; Parsed_data.zip : results and statistics of the experiments; script_adversarial_v3.py : Python script used to generate the results本仓库包含用于复现论文《通过演化对抗实例评估深度学习算法选择模型的鲁棒性》的代码与数据。 本仓库包含以下文件： Data.zip：内含数据集中的原始实例； Models.zip：论文中使用的经训练的深度神经网络（Deep Neural Networks）模型； New_instances.zip：采用该论文提出的方法生成的对抗实例； Parsed_data.zip：实验结果与统计数据； script_adversarial_v3.py：用于生成实验结果的Python脚本