Skip to main content

Advertisement

Table 5 Performance results of extracting attribute values using subject-attribute and object-attribute models (P, R, F1 represent precision, recall and F1-score, respectively)

From: Automated extraction of attributes from natural language attribute-based access control (ABAC) Policies

Dataset Subject-attribute Object-attribute
  P R F 1 P R F 1
iTrust 0.97 0.99 0.98 0.91 0.90 0.90
Collected ACP 0.93 0.93 0.93 0.93 0.95 0.94
IBM App 0.95 0.96 0.96 0.92 0.92 0.92
CyberChair 0.97 0.98 0.97 0.88 0.87 0.88
Document fold 0.91 0.80 0.85 0.75 0.69 0.71
  1. The first four rows show the performance of the model when tested on in-domain data whilst the last row represents how the system would perform on out-of-domain data