CN116057520A - 训练子模块并且防止ai模块的捕获的方法 - Google Patents

训练子模块并且防止ai模块的捕获的方法 Download PDF

Info

Publication number
CN116057520A
CN116057520A CN202180058003.9A CN202180058003A CN116057520A CN 116057520 A CN116057520 A CN 116057520A CN 202180058003 A CN202180058003 A CN 202180058003A CN 116057520 A CN116057520 A CN 116057520A
Authority
CN
China
Prior art keywords
module
input data
input
data
models
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202180058003.9A
Other languages
English (en)
Chinese (zh)
Inventor
A·J·沙阿
M·S·帕尔玛
M·T·雅什
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Robert Bosch GmbH
Bosch Global Software Technologies Pvt Ltd
Original Assignee
Robert Bosch GmbH
Robert Bosch Engineering and Business Solutions Pvt Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Robert Bosch GmbH, Robert Bosch Engineering and Business Solutions Pvt Ltd filed Critical Robert Bosch GmbH
Publication of CN116057520A publication Critical patent/CN116057520A/zh
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/10—Protecting distributed programs or content, e.g. vending or licensing of copyrighted material ; Digital rights management [DRM]
    • G06F21/12—Protecting executable software
    • G06F21/121—Restricting unauthorised execution of programs
    • G06F21/125—Restricting unauthorised execution of programs by manipulating the program code, e.g. source code, compiled code, interpreted code, machine code
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
    • G06F21/55—Detecting local intrusion or implementing counter-measures
    • G06F21/552—Detecting local intrusion or implementing counter-measures involving long-term monitoring or reporting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
    • G06F21/55—Detecting local intrusion or implementing counter-measures
    • G06F21/554—Detecting local intrusion or implementing counter-measures involving event detection and direct action
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
    • G06F21/57—Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
    • G06F21/577—Assessing vulnerabilities and evaluating computer system security
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Mathematical Physics (AREA)
  • Multimedia (AREA)
  • Technology Law (AREA)
  • Image Analysis (AREA)
  • Character Discrimination (AREA)
  • Computer And Data Communications (AREA)
CN202180058003.9A 2020-08-06 2021-07-27 训练子模块并且防止ai模块的捕获的方法 Pending CN116057520A (zh)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
IN202041033610 2020-08-06
IN202041033610A IN202041033610A (cg-RX-API-DMAC7.html) 2020-08-06 2020-08-06
PCT/EP2021/071022 WO2022028956A1 (en) 2020-08-06 2021-07-27 A method of training a submodule and preventing capture of an ai module

Publications (1)

Publication Number Publication Date
CN116057520A true CN116057520A (zh) 2023-05-02

Family

ID=77207176

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202180058003.9A Pending CN116057520A (zh) 2020-08-06 2021-07-27 训练子模块并且防止ai模块的捕获的方法

Country Status (5)

Country Link
US (1) US12547709B2 (cg-RX-API-DMAC7.html)
EP (1) EP4193278A1 (cg-RX-API-DMAC7.html)
CN (1) CN116057520A (cg-RX-API-DMAC7.html)
IN (1) IN202041033610A (cg-RX-API-DMAC7.html)
WO (1) WO2022028956A1 (cg-RX-API-DMAC7.html)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10657262B1 (en) * 2014-09-28 2020-05-19 Red Balloon Security, Inc. Method and apparatus for securing embedded device firmware
EP4627485A1 (en) * 2022-11-29 2025-10-08 Robert Bosch GmbH A method to prevent exploitation of an ai module in an ai system
CN116054997B (zh) * 2023-01-15 2026-04-21 北京东方棱镜科技有限公司 基于信息增益值的反制目标关键数据采集系统

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110249331A (zh) * 2017-01-30 2019-09-17 微软技术许可有限责任公司 针对入侵检测的连续学习

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2399187B (en) * 2002-07-24 2005-06-15 Rolls Royce Plc Method of generating a multifidelity model of a system
US9085958B2 (en) * 2013-09-19 2015-07-21 Sas Institute Inc. Control variable determination to maximize a drilling rate of penetration
US10536357B2 (en) * 2015-06-05 2020-01-14 Cisco Technology, Inc. Late data detection in data center
US11042784B2 (en) * 2017-09-15 2021-06-22 M37 Inc. Machine learning system and method for determining or inferring user action and intent based on screen image analysis
US11023593B2 (en) 2017-09-25 2021-06-01 International Business Machines Corporation Protecting cognitive systems from model stealing attacks
CN112189360B (zh) * 2018-03-20 2024-03-22 瑞典爱立信有限公司 用于操作和管理网络内的受限设备的方法和装置

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110249331A (zh) * 2017-01-30 2019-09-17 微软技术许可有限责任公司 针对入侵检测的连续学习

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
WEILIN XU等: "Feature Squeezing:Detecting Adversarial Examples in Deep Neural Networks", 《IN NETWORK AND DISTRIBUTED SYSTEMS SECURITY SYMPOSIUM》, 21 February 2018 (2018-02-21), pages 1 - 15 *

Also Published As

Publication number Publication date
US20230289436A1 (en) 2023-09-14
US12547709B2 (en) 2026-02-10
WO2022028956A1 (en) 2022-02-10
IN202041033610A (cg-RX-API-DMAC7.html) 2022-02-11
EP4193278A1 (en) 2023-06-14

Similar Documents

Publication Publication Date Title
US20230306107A1 (en) A Method of Training a Submodule and Preventing Capture of an AI Module
Veeranna et al. Using semantic similarity for multi-label zero-shot classification of text documents
US20210224688A1 (en) Method of training a module and method of preventing capture of an ai module
US12547709B2 (en) Method of training a submodule and preventing capture of an AI module
WO2023072702A1 (en) A method of training a submodule and preventing capture of an ai module
US20230376752A1 (en) A Method of Training a Submodule and Preventing Capture of an AI Module
US12541711B2 (en) Method of training a module and method of preventing capture of an AI module
US20240386111A1 (en) A Method of Training a Submodule and Preventing Capture of an AI Module
US20250165593A1 (en) A Method to Prevent Capturing of an AI Module and an AI System Thereof
US20230267200A1 (en) A Method of Training a Submodule and Preventing Capture of an AI Module
US20240061932A1 (en) A Method of Training a Submodule and Preventing Capture of an AI Module
US12613957B2 (en) Method of preventing capture of an AI module and an AI system thereof
US12212682B2 (en) Method of preventing capture of an AI module and an AI system thereof
US12032688B2 (en) Method of training a module and method of preventing capture of an AI module
US20250272390A1 (en) A Method to Prevent Exploitation of AI Module in an AI System
WO2024115579A1 (en) A method to prevent exploitation of an ai module in an ai system
WO2024105036A1 (en) A method of assessing vulnerability of an ai system and a framework thereof

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination