Skip to main content
. Author manuscript; available in PMC: 2022 Aug 15.
Published in final edited form as: Cancer Biomark. 2022;33(2):185–198. doi: 10.3233/CBM-210306

Figure 1.

Figure 1

Average MIA accuracy scores toward the MT-CNN models with vocabulary of baseline (circle), keywords appearing all six registries (I6, square), 10,000 keywords of highest mutual information (MI10000, diamond), and 2,000 keywords of highest mutual information (MI2000, triangle) across (a) all the attack models, (b) attack models to the class labels with average training samples < 100, (c) ≥ 100 and < 1000, (d) ≥ 1000 and < 10000, (e) ≥ 10000.