MIT Press

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 detection		precision	recall	F1	accuracy
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 detection		precision	recall	F1	accuracy
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%

View Large

This Feature Is Available To Subscribers Only