Pheme
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
PHEME
69.2Accuracy
26
PHEME
56.86DeepWordBug ASR
16
PHEME New Attacks: ExplainDrive (test)
82.91Accuracy
15
Pheme
87.7Precision
14
PHEME (test)
66.6Macro-F1
12
Pheme
87.2Accuracy
11
PHEME Known Attacks: DeepWordBug, TFAdjusted, TREPAT (test)
85.59Accuracy
10
PHEME
0.646Macro F1
9
PHEME
0.018ECE
6
PHEME
0.852AUC
6
PHEME
81Precision@10
5
Pheme
87.2Accuracy
1