redaction Archive

Machine learning system can descramble pixelated/blurred redactions 83% of the time

A joint UT Austin/Cornell team has taught a machine learning system based on the free/open Torch library to correctly guess the content of pixellated or blurred redactions with high accuracy: for masked faces that humans correctly guess 0.19% of the time, the system can make a correct guess 83% of the time, when given five tries. Redaction errors have plagued data-releases since the …