Supplementary materials of the paper entitled: "Generating Natural Language Requirements via 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: adversarial_samples.ipynb B2: Baseline.ipynb FIle C: Result Tables (.xlsx) C1: Table of perturbed outputs in Webex C2: Table of perturbed outputs in Zoom C3: Table of perturbed outputs in Teams C4: Table of perturbed outputs in Word C5: Table of perturbed outputs in PowerPoint C6: Table of perturbed outputs in Excel (Excel) File D: Trend of Adversarial Shifts (Graphs) D1: Adversarial shifts of office suit (LSTM) D2: Adversarial shifts of video conferencing suit (LSTM) D3: Non-Adversarial shifts of office suit (LSTM) D4: Non-Adversarial shifts of video conferencing suit(LSTM) D5: Adversarial shifts of office suit (GRU) D6: Adversarial shifts of video conferencing suit (GRU) D7: Non-Adversarial shifts of office suit (GRU) D8: Non-Adversarial shifts of video conferencing suit(GRU) D9: Adversarial shifts of office suit (Bi-LSTM) D10: Adversarial shifts of video conferencing suit (Bi-LSTM) D11: Non-Adversarial shifts of office suit (Bi-LSTM) D12: Non-Adversarial shifts of video conferencing suit(Bi-LSTM) File E: Adversarial Examples (.pdf) E1: Adversarial vs original in Webex E2: Adversarial vs original in Zoom E3: Adversarial vs original in Teams E4: Adversarial vs original in Word E5: Adversarial vs original in PowerPoint E6: Adversarial vs original in Excel File F: Questionnaire