ALEXANDRIA, Va., Nov. 18 -- United States Patent no. 12,475,225, issued on Nov. 18, was assigned to CrowdStrike Inc. (Sunnyvale, Calif.).

"Aggressive embedding dropout in embedding-based malware detection" was invented by Diana Bolocan (Galati, Romania), Mihaela-Petruta Gaman (Bucharest, Romania) and Marian Radu (Bucharest, Romania).

According to the abstract* released by the U.S. Patent & Trademark Office: "Malware is detected using an embedding-based machine learning model. The model generates embeddings using byte n-grams. A feature importance operation reveals that only a subset of the embeddings is required to detect malware. In some cases, even a single embedding is adequate and retains 99% detection capabilities. An aggressive embe...