Prompting Creative Requirements via Traceable and Adversarial Examples in Deep Learning

File A: Datasets (.txt) A1: Webex A2: Zoom A3: Teams A4: Word A5: PowerPoint A6: Excel File B: Python Code (Both ours and baseline) B1: pert_class.ipynb B2: Baseline.ipynb File C: Trend of Adversarial Shifts (Graphs) C1: Webex Adversarial Shifts C2: Zoom Adversarial Shifts C3: Teams Adversarial Shifts C4: Word Adversarial Shifts C5: Powerpoint Adversarial Shifts C6: Excel Adversarial Shifts File D: Trend of Non-Adversarial Shifts (Graphs) D1: Webex Non-Adversarial Shifts D2: Zoom Non-Adversarial Shifts D3: Teams Non-Adversarial Shifts D4: Word Non-Adversarial Shifts D5: Powerpoint Non-Adversarial Shifts D6: Excel Non-Adversarial Shifts本数据集的文件构成如下： 文件组A：.txt格式数据集，包含： A1：Webex A2：Zoom A3：Teams A4：Word A5：PowerPoint A6：Excel 文件组B：Python代码（涵盖自研代码与基线代码），包含： B1：pert_class.ipynb B2：Baseline.ipynb 文件组C：对抗偏移趋势图，包含： C1：Webex对抗偏移趋势图 C2：Zoom对抗偏移趋势图 C3：Teams对抗偏移趋势图 C4：Word对抗偏移趋势图 C5：PowerPoint对抗偏移趋势图 C6：Excel对抗偏移趋势图 文件组D：非对抗偏移趋势图，包含： D1：Webex非对抗偏移趋势图 D2：Zoom非对抗偏移趋势图 D3：Teams非对抗偏移趋势图 D4：Word非对抗偏移趋势图 D5：PowerPoint非对抗偏移趋势图 D6：Excel非对抗偏移趋势图