Secure and private machine learning View Homepage


Ontology type: schema:MonetaryGrant     


Grant Info

YEARS

2016-2018

FUNDING AMOUNT

370000 AUD

ABSTRACT

This project intends to answer the question: How can machines learn from data when participants behave maliciously for personal gain? Machine learning and statistics are used in many technologies where participants have an incentive to game the system (eg internet ad placement, e-commerce rating systems, credit risk in finance, health analytics and smart utility grids). However, little is known about how well state-of-the-art statistical inference techniques fare when data is manipulated by a malicious participant. The project's outcomes aim to ensure that statistical analysis is accurate while preserving data privacy, providing theoretical foundations of secure machine learning in adversarial domains. Potential applications range from cybersecurity defences to measures for balancing security and privacy interests. More... »

URL

http://purl.org/au-research/grants/arc/DE160100584

Related SciGraph Publications

  • 2018-01. Differentially private counting of users’ spatial regions in KNOWLEDGE AND INFORMATION SYSTEMS
  • JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/2201", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/2208", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/2208", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/2208", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "type": "DefinedTerm"
          }
        ], 
        "amount": {
          "currency": "AUD", 
          "type": "MonetaryAmount", 
          "value": "370000"
        }, 
        "description": "This project intends to answer the question: How can machines learn from data when participants behave maliciously for personal gain? Machine learning and statistics are used in many technologies where participants have an incentive to game the system (eg\u00a0internet ad placement, e-commerce rating systems, credit risk in finance, health analytics and smart utility grids). However, little is known about how well state-of-the-art statistical inference techniques fare when data is manipulated by a malicious participant. The project's outcomes aim to ensure that statistical analysis is accurate while preserving data privacy, providing theoretical foundations of secure machine learning in adversarial domains. Potential applications range from cybersecurity defences to measures for balancing security and privacy interests.", 
        "endDate": "2018-12-31T00:00:00Z", 
        "funder": {
          "id": "https://www.grid.ac/institutes/grid.413452.5", 
          "type": "Organization"
        }, 
        "id": "sg:grant.5127611", 
        "identifier": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "5127611"
            ]
          }, 
          {
            "name": "arc_id", 
            "type": "PropertyValue", 
            "value": [
              "DE160100584"
            ]
          }
        ], 
        "inLanguage": [
          "en"
        ], 
        "keywords": [
          "statistical analysis", 
          "private machine learning", 
          "many technologies", 
          "health analytics", 
          "malicious participants", 
          "machine learning", 
          "security", 
          "incentives", 
          "secure machine", 
          "smart utility grids", 
          "cybersecurity defences", 
          "statistics", 
          "question", 
          "system", 
          "credit risk", 
          "internet ad placement", 
          "state", 
          "project outcomes", 
          "adversarial domains", 
          "data privacy", 
          "commerce rating systems", 
          "personal gain", 
          "art", 
          "privacy interests", 
          "project", 
          "measures", 
          "finance", 
          "statistical inference techniques", 
          "theoretical foundation", 
          "participants", 
          "machine", 
          "potential applications", 
          "data"
        ], 
        "name": "Secure and private machine learning", 
        "recipient": [
          {
            "id": "https://www.grid.ac/institutes/grid.1008.9", 
            "type": "Organization"
          }
        ], 
        "sameAs": [
          "https://app.dimensions.ai/details/grant/grant.5127611"
        ], 
        "sdDataset": "grants", 
        "sdDatePublished": "2019-03-07T11:16", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com.uberresearch.data.processor/core_data/20181219_192338/projects/base/arc_projects.xml.gz", 
        "startDate": "2016-01-01T00:00:00Z", 
        "type": "MonetaryGrant", 
        "url": "http://purl.org/au-research/grants/arc/DE160100584"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/grant.5127611'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/grant.5127611'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/grant.5127611'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/grant.5127611'


     

    This table displays all metadata directly associated to this object as RDF triples.

    70 TRIPLES      19 PREDICATES      54 URIs      46 LITERALS      4 BLANK NODES

    Subject Predicate Object
    1 sg:grant.5127611 schema:about anzsrc-for:2201
    2 anzsrc-for:2208
    3 schema:amount N3ea201c52bf347ada1ea561126cc6ac7
    4 schema:description This project intends to answer the question: How can machines learn from data when participants behave maliciously for personal gain? Machine learning and statistics are used in many technologies where participants have an incentive to game the system (eg internet ad placement, e-commerce rating systems, credit risk in finance, health analytics and smart utility grids). However, little is known about how well state-of-the-art statistical inference techniques fare when data is manipulated by a malicious participant. The project's outcomes aim to ensure that statistical analysis is accurate while preserving data privacy, providing theoretical foundations of secure machine learning in adversarial domains. Potential applications range from cybersecurity defences to measures for balancing security and privacy interests.
    5 schema:endDate 2018-12-31T00:00:00Z
    6 schema:funder https://www.grid.ac/institutes/grid.413452.5
    7 schema:identifier N083c7377c98e47e38322292f20c7a11b
    8 Na729dc505d114dfdb6e0440773e26ad8
    9 schema:inLanguage en
    10 schema:keywords adversarial domains
    11 art
    12 commerce rating systems
    13 credit risk
    14 cybersecurity defences
    15 data
    16 data privacy
    17 finance
    18 health analytics
    19 incentives
    20 internet ad placement
    21 machine
    22 machine learning
    23 malicious participants
    24 many technologies
    25 measures
    26 participants
    27 personal gain
    28 potential applications
    29 privacy interests
    30 private machine learning
    31 project
    32 project outcomes
    33 question
    34 secure machine
    35 security
    36 smart utility grids
    37 state
    38 statistical analysis
    39 statistical inference techniques
    40 statistics
    41 system
    42 theoretical foundation
    43 schema:name Secure and private machine learning
    44 schema:recipient https://www.grid.ac/institutes/grid.1008.9
    45 schema:sameAs https://app.dimensions.ai/details/grant/grant.5127611
    46 schema:sdDatePublished 2019-03-07T11:16
    47 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    48 schema:sdPublisher N8418494212834cd8a154fa009427bf4d
    49 schema:startDate 2016-01-01T00:00:00Z
    50 schema:url http://purl.org/au-research/grants/arc/DE160100584
    51 sgo:license sg:explorer/license/
    52 sgo:sdDataset grants
    53 rdf:type schema:MonetaryGrant
    54 N083c7377c98e47e38322292f20c7a11b schema:name arc_id
    55 schema:value DE160100584
    56 rdf:type schema:PropertyValue
    57 N3ea201c52bf347ada1ea561126cc6ac7 schema:currency AUD
    58 schema:value 370000
    59 rdf:type schema:MonetaryAmount
    60 N8418494212834cd8a154fa009427bf4d schema:name Springer Nature - SN SciGraph project
    61 rdf:type schema:Organization
    62 Na729dc505d114dfdb6e0440773e26ad8 schema:name dimensions_id
    63 schema:value 5127611
    64 rdf:type schema:PropertyValue
    65 anzsrc-for:2201 schema:inDefinedTermSet anzsrc-for:
    66 rdf:type schema:DefinedTerm
    67 anzsrc-for:2208 schema:inDefinedTermSet anzsrc-for:
    68 rdf:type schema:DefinedTerm
    69 https://www.grid.ac/institutes/grid.1008.9 schema:Organization
    70 https://www.grid.ac/institutes/grid.413452.5 schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...