WO2023103763 - METHODS, SYSTEMS AND COMPUTER PROGRAM PRODUCTS FOR PROTECTING A DEEP REINFORCEMENT LEARNING AGENT
National phase entry:
Publication Number
WO/2023/103763
Publication Date
15.06.2023
International Application No.
PCT/CN2022/133356
International Filing Date
22.11.2022
Title **
[English]
METHODS, SYSTEMS AND COMPUTER PROGRAM PRODUCTS FOR PROTECTING A DEEP REINFORCEMENT LEARNING AGENT
[French]
PROCÉDÉS, SYSTÈMES ET PRODUITS-PROGRAMMES INFORMATIQUES SERVANT À PROTÉGER UN AGENT D'APPRENTISSAGE PAR RENFORCEMENT PROFOND
Applicants **
HUAWEI TECHNOLOGIES CO., LTD.
Inventors
ALHUSSEIN, Omar Ahmad Mohammad
ASHWOOD-SMITH, Peter
Priority Data
17/546,768
09.12.2021
US
Application details
| Total Number of Claims/PCT | * |
| Number of Independent Claims | * |
| Number of Priorities | * |
| Number of Multi-Dependent Claims | * |
| Number of Drawings | * |
| Pages for Publication | * |
| Number of Pages with Drawings | * |
| Pages of Specification | * |
| * | |
| Number of Office Actions | * |
| * | |
International Searching Authority |
CNIPA
* |
| Recordal of a Change of the Applicant's Name/Address |
Change of Applicant's Name and Address
* |
| Type of Assignment |
The Standard Agent's Assignment
* |
| Applicant's Legal Status |
Legal Entity
* |
| * | |
| * | |
| * | |
| * | |
| * | |
| Entry into National Phase under |
Chapter I
* |
| Patent Delivery |
Send the Letters Patent by Courier
* |
| Translation |
|
* The data is based on automatic recognition. Please verify and amend if necessary.
** IP-Coster compiles data from publicly available sources. If this data includes your personal information, you can contact us to request its removal.
Quotation for National Phase entry
| Country | Stages | Total | |
|---|---|---|---|
| China | Filing, Examination, Granting | 2527 | |
| EPO | Filing, Examination, Granting | 22178 | |
| Japan | Filing, Examination, Granting | 2870 | |
| South Korea | Filing, Examination, Granting | 3591 | |
| USA | Filing, Examination, Granting | 9340 |
Total:
40,506
The term for entry into the National Phase has expired. This quotation is for informational purposes only
Contact Us
Abstract[English]
There are provided a method, system and computer program product for preventing unauthorized use of a deep reinforcement learning agent. The DRL agents are trained to behave as expected only when they observe the one or more required secret operational keys. In some embodiments, the DRL agents are further trained to operate at a diminished capacity when the one or more required secret operational keys are unused.[French]
L'invention concerne un procédé, un système et un produit-programme informatique servant à empêcher l'utilisation non autorisée d'un agent d'apprentissage par renforcement profond (DRL). Les agents DRL sont formés pour ne se comporter conformément à certaines attentes que lorsqu'ils observent la ou les clés d'exploitation secrètes requises. Selon certains modes de réalisation, les agents DRL sont de plus formés pour s'exécuter à capacité réduite lorsque la ou les clés d'exploitation secrètes requises sont inutilisées.