公开(公告)号：US20220058245A1

公开(公告)日：2022-02-24

申请号：US17453311

申请日：2021-11-02

Applicant: Intel Corporation

Inventor： OLEG POGORELIK ,  SHEFY GUR-ARY ,  ADIR ABRAHAM ,  DAVID ALHANATI ,  ANGELO MOSCATI ,  ALEX NAYSHTUT ,  DENIS KLIMOV

IPC: G06F21/16 ,  G06T1/00 ,  G06F21/62

Abstract: In one example an apparatus comprises a memory and a processor to receive, in an edge node of a secure network, a first file, determine that the first file is addressed to a recipient outside the secure network, and in response to a determination that the first file is addressed to a destination outside the secure network, to generate a watermark that identifies a transmitter of the document, a recipient of the document, and comprises a digital signature of the first file, embed the watermark in the first file to generate a watermarked file, and pass the watermarked file to an input/output system for transmission out of the secure network. Other examples may be described.

公开(公告)号：US20210319098A1

公开(公告)日：2021-10-14

申请号：US17254235

申请日：2019-04-23

Applicant: INTEL CORPORATION

Inventor： OLEG POGORELIK ,  ALEX NAYSHTUT ,  OMER BEN-SHALOM ,  DENIS KLIMOV ,  RAIZY KELLERMANN ,  GUY BARNHART-MAGEN ,  VADIM SUKHOMLINOV

IPC: G06F21/55 ,  G06N20/00 ,  G06N5/04

Abstract: Techniques and apparatuses to harden AI systems against various attacks are provided. Among the different techniques and apparatuses, is provided, techniques and apparatuses that expand the domain for an inference model to include both visible classes and well as hidden classes. The hidden classes can be used to detect possible probing attacks against the model.