Adversarial Text Detection on RTMR
86.9F1 ScoreVoteTRANS_same
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| VoteTRANS_sameTarget Model=DistilBERT, Attack=IGA, Auxiliary Attack=IGA2023.06 | 86.9 | 90.4 | |
| VoteTRANS_sameTarget Model=DistilBERT, Attack=PWWS, Auxiliary Attack=PWWS2023.06 | 83.8 | 88 | |
| VoteTRANS_diffTarget Model=DistilBERT, Attack=IGA, Auxiliary Attack=PWWS2023.06 | 80.5 | 82.4 | |
| VoteTRANS_sameTarget Model=DistilBERT, Attack=BAE, Auxiliary Attack=BAE2023.06 | 79.1 | 80.8 | |
| FGWSTarget Model=DistilBERT, Attack=PWWS, Detector training configuration=(DistilBERT, AG News, PWWS)2023.06 | 78.9 | 67.8 | |
| WDRTarget Model=DistilBERT, Attack=PWWS, Detector training configuration=(DistilBERT, AG News, PWWS)2023.06 | 75.8 | 78.5 | |
| WDRTarget Model=DistilBERT, Attack=IGA, Detector training configuration=(DistilBERT, AG News, PWWS)2023.06 | 73.7 | 85.4 | |
| WDRTarget Model=DistilBERT, Attack=BAE, Detector training configuration=(DistilBERT, AG News, PWWS)2023.06 | 71 | 75.2 | |
| FGWSTarget Model=DistilBERT, Attack=IGA, Detector training configuration=(DistilBERT, AG News, PWWS)2023.06 | 68.1 | 55.2 | |
| VoteTRANS_diffTarget Model=DistilBERT, Attack=BAE, Auxiliary Attack=PWWS2023.06 | 65.5 | 60.8 | |
| FGWSTarget Model=DistilBERT, Attack=BAE, Detector training configuration=(DistilBERT, AG News, PWWS)2023.06 | 29.4 | 18.5 |