CPC G06F 21/554 (2013.01) [G06F 18/21 (2023.01); G06F 18/2431 (2023.01); G06F 21/31 (2013.01); G06N 5/04 (2013.01); G06N 20/20 (2019.01); G06V 10/25 (2022.01); G06V 10/82 (2022.01); G06V 20/41 (2022.01); G06V 20/52 (2022.01); G06V 30/19173 (2022.01); G06V 30/274 (2022.01); G08B 13/19613 (2013.01); G08B 29/188 (2013.01); H04N 23/90 (2023.01); G06Q 50/265 (2013.01); G06V 20/44 (2022.01)] | 16 Claims |
1. A method, comprising:
determining a set of access primitives and a set of semantic primitives, wherein the set of semantic primitives is determined by:
determining image data;
extracting feature values from the image data using a feature detection model; and
generating the set of semantic primitives using a set of sub-models, each specific to a different subset of semantic primitives, based on the extracted feature values;
determining a correlation between the set of access primitives and the set of semantic primitives;
determining a context classification based on the correlation; and
determining a security risk based on the context classification.
|