US Patent Issued to B. G. NEGEV TECHNOLOGIES AND APPLICATIONS, AT BEN-GURION UNIVERSITY, University of Connecticut on April 29 for "Systems and methods for protecting machine learning models against adversarial attacks" (American, Israeli Inventors)

ALEXANDRIA, Va., June 9 -- United States Patent no. 12,287,892, issued on April 29, was assigned to B. G. NEGEV TECHNOLOGIES AND APPLICATIONS LTD., AT BEN-GURION UNIVERSITY (Beer Sheva, Israel) and University of Connecticut (Farmington, Conn.).

"Systems and methods for protecting machine learning models against adversarial attacks" was invented by Bahram Javidi (Farmington, Conn.) and Adrian Stern (Beer Sheva, Israel).

According to the abstract* released by the U.S. Patent & Trademark Office: "Embodiments pertain to systems configured to and methods for analyzing a scene comprising one or more objects. The system may be configured to perform the following: obtaining a set of optically encrypted image data describing a scene, including app...