Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020142110 - SECURING SYSTEMS EMPLOYING ARTIFICIAL INTELLIGENCE

Publication Number WO/2020/142110
Publication Date 09.07.2020
International Application No. PCT/US2019/028687
International Filing Date 23.04.2019
IPC
G06N 3/08 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
G06N 3/04 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architecture, e.g. interconnection topology
G06N 20/00 2019.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
CPC
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06N 3/04
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
Applicants
  • INTEL CORPORATION [US]/[US]
Inventors
  • POGORELIK, Oleg
  • NAYSHTUT, Alex
  • BEN-SHALOM, Omer
  • KLIMOV, Denis
  • KELLERMANN, Raizy
  • BARNHART-MAGEN, Guy
  • SUKHOMLINOV, Vadim
Agents
  • DYER, Richard A.
Priority Data
62/786,94131.12.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SECURING SYSTEMS EMPLOYING ARTIFICIAL INTELLIGENCE
(FR) SYSTÈMES DE SÉCURISATION UTILISANT UNE INTELLIGENCE ARTIFICIELLE
Abstract
(EN)
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.
(FR)
L'invention concerne des techniques et des appareils permettant de durcir des systèmes d'intelligence artificielle contre diverses attaques. Parmi les différents techniques et appareils, l'invention concerne des techniques et des appareils qui étendent le domaine pour un modèle d'inférence afin d'inclure à la fois des classes visibles et des classes cachées. Les classes cachées peuvent être utilisées pour détecter de possibles attaques par sondage contre le modèle.
Also published as
Latest bibliographic data on file with the International Bureau