Fig. 3: Forecasting the correctness of popular identification techniques with the PYC-MB model.
From: A scaling law to model the effectiveness of identification techniques
Each panel shows the empirical correctness κ (black dots) in four identification scenarios, along with our prediction \(\widehat{\kappa }\) (solid blue line) fitted on the empirical κ scores. a Identification of mobile phone users from their pseudonymized 1-hop social network (IIG-1, n = 43, 000 phones) by Creţu et al.25. b Facial recognition using Google FaceNet V8 (FACEREC-2, n = 1M faces) by Kemelmacher-Shlizerman et al.56. c Authorship attribution in textual data using Deep Learning (TEXT-1, n = 500 authors) by Saedi et al.29. d Exact matching using simple browser fingerprints (HTTP accept, cookies and JavaScript enabled, timezone, display size, installed fonts, plugins, user agent, video) collected by Panopticlick (WEB-2, n = 5.5M fingerprints)57.
