Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for determining a confidence factor for a sensitive type. The method includes applying a set of matching procedures to cells in a structured data set, the structured data set comprising columns and/or rows. The method also includes counting hit counts for the cells, the hit counts corresponding to successful matches. The method also includes counting null counts for the cells, the null counts corresponding to cells having null or invalid values. The method also includes counting mishit counts for the cells, the mishit counts corresponding to cells that are not null and do not result in a match. The method also includes calculating the confidence factor based on the hit counts, the null counts, and the mishit counts, the confidence factor providing an effective probability that cells in the structured data set is of the sensitive type.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for determining a confidence factor for a sensitive type. The method includes applying a set of matching procedures to cells in a structured data set, the structured data set comprising columns and/or rows. The method also includes counting hit counts for the cells, the hit counts corresponding to successful matches. The method also includes counting null counts for the cells, the null counts corresponding to cells having null or invalid values. The method also includes counting mishit counts for the cells, the mishit counts corresponding to cells that are not null and do not result in a match. The method also includes calculating the confidence factor based on the hit counts, the null counts, and the mishit counts, the confidence factor providing an effective probability that cells in the structured data set is of the sensitive type.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for determining a confidence factor for a sensitive type. The method includes applying a set of matching procedures to cells in a structured data set, the structured data set comprising columns and/or rows. The method also includes counting hit counts for the cells, the hit counts corresponding to successful matches. The method also includes counting null counts for the cells, the null counts corresponding to cells having null or invalid values. The method also includes counting mishit counts for the cells, the mishit counts corresponding to cells that are not null and do not result in a match. The method also includes calculating the confidence factor based on the hit counts, the null counts, and the mishit counts, the confidence factor providing an effective probability that cells in the structured data set is of the sensitive type.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for determining a confidence factor for a sensitive type. The method includes applying a set of matching procedures to cells in a structured data set, the structured data set comprising columns and/or rows. The method also includes counting hit counts for the cells, the hit counts corresponding to successful matches. The method also includes counting null counts for the cells, the null counts corresponding to cells having null or invalid values. The method also includes counting mishit counts for the cells, the mishit counts corresponding to cells that are not null and do not result in a match. The method also includes calculating the confidence factor based on the hit counts, the null counts, and the mishit counts, the confidence factor providing an effective probability that cells in the structured data set is of the sensitive type.

Abstract: Methods and systems for identifying sensitive information are provided. The method includes tokenizing labeled data into first word sequences, the labeled data including sensitive information. The method includes associating the labeled sensitive information with tags. The method includes determining that the first word sequences and the tags satisfy conditions defined by feature functions. The method includes calculating a local maximum of a likelihood function to determine a weight. The method includes tokenizing unlabeled data into second word sequences, the unlabeled data including sensitive information. The method includes executing each feature function based on their weights, the second word sequences, and tag sequences. The method includes selecting tag sequences that maximize probabilities of the second word sequences based on the likelihood function. The method includes identifying sensitive information in the unlabeled data based on the selected tag sequences.