US Patent Issued to International Business Machines on Nov. 25 for "Distributed adversarial training for robust deep neural networks" (Massachusetts, New York Inventors)

ALEXANDRIA, Va., Nov. 25 -- United States Patent no. 12,481,874, issued on Nov. 25, was assigned to International Business Machines Corp. (Armonk, N.Y.).

"Distributed adversarial training for robust deep neural networks" was invented by Sijia Liu (Somerville, Mass.), Gaoyuan Zhang (Medford, Mass.), Pin-Yu Chen (White Plains, N.Y.), Chuang Gan (Cambridge, Mass.) and Songtao Lu (White Plains, N.Y.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Scalable distributed adversarial training techniques for robust deep neural networks are provided. In one aspect, a method for adversarial training of a deep neural network-based model by distributed computing machines M includes, by distributed computing machines M: obt...