View in EDS

GeoPM-DMEIRL: A deep inverse reinforcement learning security trajectory generation framework with serverless computing.

Saved in:
Bibliographic Details
Title: GeoPM-DMEIRL: A deep inverse reinforcement learning security trajectory generation framework with serverless computing.
Authors: Huang, Yi-rui1 (AUTHOR), Zhang, Jing1 (AUTHOR) jing165455@126.com, Hou, Hong-ming1 (AUTHOR), Ye, Xiu-cai2 (AUTHOR), Chen, Yi3 (AUTHOR)
Source: Future Generation Computer Systems. May2024, Vol. 154, p123-139. 17p.
Subjects: Amazon Web Services Inc., Deep reinforcement learning, Reinforcement learning, Deep learning, Data privacy, Weight training, Location-based services
Abstract: Vehicle trajectory data is essential for traffic management and location-based services. However, the release of trajectories raises serious privacy concerns because they contain sensitive information, such as home addresses and workplaces, etc, making it indispensable to consider privacy protection when releasing trajectory data. It is urgent to reconcile data utility with privacy in trajectory generation calls for advanced methods that adhere to real-world traffic rules. Leveraging serverless computing for deep learning provides an efficient solution, bypassing infrastructure complexities to handle the scale trajectory data. In this paper, a Geo-Piecewise Mechanism Deep Maximum Entropy Inverse Reinforcement Learning (GeoPM-DMEIRL) is proposed for secure trajectory generation, which consists of three key components, namely GeoPM, A2C reinforcement learning and DMEIRL. Firstly, GeoPM is a novel local differential privacy mechanism that incorporates Geo-aware gridding techniques. The Piecewise Mechanism is used to perturb the user trajectory while ensuring that the perturbed trajectory conforms to real-world traffic rules. Secondly, an A2C reinforcement learning network is refined to train the optimal trajectory generation strategy. Thirdly, Deep Maximum Entropy Inverse Reinforcement Learning is improved to train the weights of the A2C reward function. Finally, real-world data are collected in the experiments and the serverless computing platform AWS Lambda is used for training the reinforcement learning models. Experimental results show that our proposed GeoPM-DMEIRL framework can effectively resist user re-identification attacks, which can improve the utility by an average of 54.605% and enhance the privacy by an average of 30.678%. Meanwhile, GeoPM-DMEIRL is able to maintain the utility of the data while protecting the privacy of the user's trajectories. • Geo-aware Piecewise Mechanism (GeoPM) is designed to protect the privacy of users' original trajectories stored in AWS S3 buckets. • The Advantage Actor–Critic (A2C) reinforcement learning network is adopted for trajectory generation. • The DMEIRL algorithm is improved to fit the reward function based on the expert demonstration trajectories. • Experiments were conducted on GeoPM-DMEIRL using real-world datasets on the serverless platform of AWS Lambda. [ABSTRACT FROM AUTHOR]
Copyright of Future Generation Computer Systems is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 175457590
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: GeoPM-DMEIRL: A deep inverse reinforcement learning security trajectory generation framework with serverless computing.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Huang%2C+Yi-rui%22">Huang, Yi-rui</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Jing%22">Zhang, Jing</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> jing165455@126.com</i><br /><searchLink fieldCode="AR" term="%22Hou%2C+Hong-ming%22">Hou, Hong-ming</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ye%2C+Xiu-cai%22">Ye, Xiu-cai</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Chen%2C+Yi%22">Chen, Yi</searchLink><relatesTo>3</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Future+Generation+Computer+Systems%22">Future Generation Computer Systems</searchLink>. May2024, Vol. 154, p123-139. 17p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Amazon+Web+Services+Inc%2E%22">Amazon Web Services Inc.</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+reinforcement+learning%22">Deep reinforcement learning</searchLink><br /><searchLink fieldCode="DE" term="%22Reinforcement+learning%22">Reinforcement learning</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Data+privacy%22">Data privacy</searchLink><br /><searchLink fieldCode="DE" term="%22Weight+training%22">Weight training</searchLink><br /><searchLink fieldCode="DE" term="%22Location-based+services%22">Location-based services</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Vehicle trajectory data is essential for traffic management and location-based services. However, the release of trajectories raises serious privacy concerns because they contain sensitive information, such as home addresses and workplaces, etc, making it indispensable to consider privacy protection when releasing trajectory data. It is urgent to reconcile data utility with privacy in trajectory generation calls for advanced methods that adhere to real-world traffic rules. Leveraging serverless computing for deep learning provides an efficient solution, bypassing infrastructure complexities to handle the scale trajectory data. In this paper, a Geo-Piecewise Mechanism Deep Maximum Entropy Inverse Reinforcement Learning (GeoPM-DMEIRL) is proposed for secure trajectory generation, which consists of three key components, namely GeoPM, A2C reinforcement learning and DMEIRL. Firstly, GeoPM is a novel local differential privacy mechanism that incorporates Geo-aware gridding techniques. The Piecewise Mechanism is used to perturb the user trajectory while ensuring that the perturbed trajectory conforms to real-world traffic rules. Secondly, an A2C reinforcement learning network is refined to train the optimal trajectory generation strategy. Thirdly, Deep Maximum Entropy Inverse Reinforcement Learning is improved to train the weights of the A2C reward function. Finally, real-world data are collected in the experiments and the serverless computing platform AWS Lambda is used for training the reinforcement learning models. Experimental results show that our proposed GeoPM-DMEIRL framework can effectively resist user re-identification attacks, which can improve the utility by an average of 54.605% and enhance the privacy by an average of 30.678%. Meanwhile, GeoPM-DMEIRL is able to maintain the utility of the data while protecting the privacy of the user's trajectories. • Geo-aware Piecewise Mechanism (GeoPM) is designed to protect the privacy of users' original trajectories stored in AWS S3 buckets. • The Advantage Actor–Critic (A2C) reinforcement learning network is adopted for trajectory generation. • The DMEIRL algorithm is improved to fit the reward function based on the expert demonstration trajectories. • Experiments were conducted on GeoPM-DMEIRL using real-world datasets on the serverless platform of AWS Lambda. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Future Generation Computer Systems is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=175457590
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.future.2024.01.001
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 17
        StartPage: 123
    Subjects:
      – SubjectFull: Amazon Web Services Inc.
        Type: general
      – SubjectFull: Deep reinforcement learning
        Type: general
      – SubjectFull: Reinforcement learning
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Data privacy
        Type: general
      – SubjectFull: Weight training
        Type: general
      – SubjectFull: Location-based services
        Type: general
    Titles:
      – TitleFull: GeoPM-DMEIRL: A deep inverse reinforcement learning security trajectory generation framework with serverless computing.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Huang, Yi-rui
      – PersonEntity:
          Name:
            NameFull: Zhang, Jing
      – PersonEntity:
          Name:
            NameFull: Hou, Hong-ming
      – PersonEntity:
          Name:
            NameFull: Ye, Xiu-cai
      – PersonEntity:
          Name:
            NameFull: Chen, Yi
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 05
              Text: May2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 0167739X
          Numbering:
            – Type: volume
              Value: 154
          Titles:
            – TitleFull: Future Generation Computer Systems
              Type: main
ResultId 1