Skip to Main Content
Table 2 
Detection results on the attacks of Section 5 in a zero-shot setting and the adaptive setting (where the discriminator is fine-tuned to a specific attacker). We report (macro) F1 score and overall accuracy. Precision, and recall of the “fake” class are reported as well.
Provenance detectionprecisionrecallF1accuracy
zero-shot full article 0.84 0.98 0.90 90% 
vanilla extension (g = 20%) 0.52 0.20 0.45 51% 
vanilla extension (g = 1%) 0.07 0.01 0.28 37% 
adaptive full article 0.93 0.94 0.94 94% 
vanilla extension (g = 20%) 0.90 0.97 0.95 95% 
vanilla extension (g = 1%) 0.91 0.95 0.94 95% 
QA extension (machine vs. human) 0.82 0.86 0.83 83% 
Provenance detectionprecisionrecallF1accuracy
zero-shot full article 0.84 0.98 0.90 90% 
vanilla extension (g = 20%) 0.52 0.20 0.45 51% 
vanilla extension (g = 1%) 0.07 0.01 0.28 37% 
adaptive full article 0.93 0.94 0.94 94% 
vanilla extension (g = 20%) 0.90 0.97 0.95 95% 
vanilla extension (g = 1%) 0.91 0.95 0.94 95% 
QA extension (machine vs. human) 0.82 0.86 0.83 83% 
Close Modal

or Create an Account

Close Modal
Close Modal