Applying Cost-Sensitive Classifiers with Reinforcement Learning to IDS View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2018-11-09

AUTHORS

Roberto Blanco , Juan J. Cilla , Samira Briongos , Pedro Malagón , José M. Moya

ABSTRACT

When using an intrusion detection system as protection against certain kind of attacks, the impact of classifying normal samples as attacks (False Positives) or attacks as normal traffic (False Negatives) is completely different. In order to prioritize the absence of one kind of error, we use reinforcement learning strategies which allow us to build a cost-sensitive meta-classifier. This classifier has been build using a DQN architecture over a MLP. While the DQN introduces extra effort during the training steps, it does not cause any penalty on the detection system. We show the feasibility of our approach for two different and commonly used datasets, achieving reductions up to 100% in the desired error by changing the rewarding strategies. More... »

PAGES

531-538

References to SciGraph publications

  • 2008-06. Instance weighting versus threshold adjusting for cost-sensitive classification in KNOWLEDGE AND INFORMATION SYSTEMS
  • 1998. Inducing cost-sensitive trees via instance weighting in PRINCIPLES OF DATA MINING AND KNOWLEDGE DISCOVERY
  • Book

    TITLE

    Intelligent Data Engineering and Automated Learning – IDEAL 2018

    ISBN

    978-3-030-03492-4
    978-3-030-03493-1

    Author Affiliations

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-030-03493-1_55

    DOI

    http://dx.doi.org/10.1007/978-3-030-03493-1_55

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1109832331


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    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/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "name": [
                "Integrated Systems Laboratory, Universidad Polit\u00e9cnica de Madrid ETSI Telecomunicaci\u00f3n, Av. Complutense 30, 28040, Madrid, Spain"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Blanco", 
            "givenName": "Roberto", 
            "id": "sg:person.010063411206.84", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010063411206.84"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "name": [
                "Integrated Systems Laboratory, Universidad Polit\u00e9cnica de Madrid ETSI Telecomunicaci\u00f3n, Av. Complutense 30, 28040, Madrid, Spain"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Cilla", 
            "givenName": "Juan J.", 
            "id": "sg:person.010660771606.18", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010660771606.18"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "name": [
                "Integrated Systems Laboratory, Universidad Polit\u00e9cnica de Madrid ETSI Telecomunicaci\u00f3n, Av. Complutense 30, 28040, Madrid, Spain"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Briongos", 
            "givenName": "Samira", 
            "id": "sg:person.014640541614.35", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014640541614.35"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Technical University of Madrid", 
              "id": "https://www.grid.ac/institutes/grid.5690.a", 
              "name": [
                "Integrated Systems Laboratory, Universidad Polit\u00e9cnica de Madrid ETSI Telecomunicaci\u00f3n, Av. Complutense 30, 28040, Madrid, Spain", 
                "Center for Computational Simulation, Universidad Polit\u00e9cnica de Madrid, Campus de Montegancedo, 28660, Boadilla del Monte, Madrid, Spain"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Malag\u00f3n", 
            "givenName": "Pedro", 
            "id": "sg:person.012400766577.71", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012400766577.71"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Technical University of Madrid", 
              "id": "https://www.grid.ac/institutes/grid.5690.a", 
              "name": [
                "Integrated Systems Laboratory, Universidad Polit\u00e9cnica de Madrid ETSI Telecomunicaci\u00f3n, Av. Complutense 30, 28040, Madrid, Spain", 
                "Center for Computational Simulation, Universidad Polit\u00e9cnica de Madrid, Campus de Montegancedo, 28660, Boadilla del Monte, Madrid, Spain"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Moya", 
            "givenName": "Jos\u00e9 M.", 
            "id": "sg:person.07662217004.56", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07662217004.56"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1080/19393555.2015.1125974", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1007650632"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neucom.2012.12.023", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1028482516"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.2478/v10065-010-0035-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1030216055"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.knosys.2016.01.025", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1039590089"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bfb0094814", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1044906515", 
              "https://doi.org/10.1007/bfb0094814"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s10115-007-0079-1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1048430917", 
              "https://doi.org/10.1007/s10115-007-0079-1"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s10115-007-0079-1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1048430917", 
              "https://doi.org/10.1007/s10115-007-0079-1"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tkde.2008.239", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061661916"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/milcis.2015.7348942", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094497395"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2018-11-09", 
        "datePublishedReg": "2018-11-09", 
        "description": "When using an intrusion detection system as protection against certain kind of attacks, the impact of classifying normal samples as attacks (False Positives) or attacks as normal traffic (False Negatives) is completely different. In order to prioritize the absence of one kind of error, we use reinforcement learning strategies which allow us to build a cost-sensitive meta-classifier. This classifier has been build using a DQN architecture over a MLP. While the DQN introduces extra effort during the training steps, it does not cause any penalty on the detection system. We show the feasibility of our approach for two different and commonly used datasets, achieving reductions up to 100% in the desired error by changing the rewarding strategies.", 
        "editor": [
          {
            "familyName": "Yin", 
            "givenName": "Hujun", 
            "type": "Person"
          }, 
          {
            "familyName": "Camacho", 
            "givenName": "David", 
            "type": "Person"
          }, 
          {
            "familyName": "Novais", 
            "givenName": "Paulo", 
            "type": "Person"
          }, 
          {
            "familyName": "Tall\u00f3n-Ballesteros", 
            "givenName": "Antonio J.", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-030-03493-1_55", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": {
          "isbn": [
            "978-3-030-03492-4", 
            "978-3-030-03493-1"
          ], 
          "name": "Intelligent Data Engineering and Automated Learning \u2013 IDEAL 2018", 
          "type": "Book"
        }, 
        "name": "Applying Cost-Sensitive Classifiers with Reinforcement Learning to IDS", 
        "pagination": "531-538", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-030-03493-1_55"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "1277e3d787878f79818b1dcb8047875680de0f3ecf16fc32c94bc42f1a115cda"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1109832331"
            ]
          }
        ], 
        "publisher": {
          "location": "Cham", 
          "name": "Springer International Publishing", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-030-03493-1_55", 
          "https://app.dimensions.ai/details/publication/pub.1109832331"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-16T04:41", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000322_0000000322/records_65005_00000000.jsonl", 
        "type": "Chapter", 
        "url": "https://link.springer.com/10.1007%2F978-3-030-03493-1_55"
      }
    ]
     

    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/pub.10.1007/978-3-030-03493-1_55'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-03493-1_55'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-03493-1_55'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-03493-1_55'


     

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

    141 TRIPLES      23 PREDICATES      34 URIs      19 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-030-03493-1_55 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N7ca8222d645244d4a0722d9fb44fdef2
    4 schema:citation sg:pub.10.1007/bfb0094814
    5 sg:pub.10.1007/s10115-007-0079-1
    6 https://doi.org/10.1016/j.knosys.2016.01.025
    7 https://doi.org/10.1016/j.neucom.2012.12.023
    8 https://doi.org/10.1080/19393555.2015.1125974
    9 https://doi.org/10.1109/milcis.2015.7348942
    10 https://doi.org/10.1109/tkde.2008.239
    11 https://doi.org/10.2478/v10065-010-0035-7
    12 schema:datePublished 2018-11-09
    13 schema:datePublishedReg 2018-11-09
    14 schema:description When using an intrusion detection system as protection against certain kind of attacks, the impact of classifying normal samples as attacks (False Positives) or attacks as normal traffic (False Negatives) is completely different. In order to prioritize the absence of one kind of error, we use reinforcement learning strategies which allow us to build a cost-sensitive meta-classifier. This classifier has been build using a DQN architecture over a MLP. While the DQN introduces extra effort during the training steps, it does not cause any penalty on the detection system. We show the feasibility of our approach for two different and commonly used datasets, achieving reductions up to 100% in the desired error by changing the rewarding strategies.
    15 schema:editor Nbeddad2ef4ad4f82a73e5af379553f97
    16 schema:genre chapter
    17 schema:inLanguage en
    18 schema:isAccessibleForFree false
    19 schema:isPartOf Ncd99e6896d6747f1ac9b06b0146000f5
    20 schema:name Applying Cost-Sensitive Classifiers with Reinforcement Learning to IDS
    21 schema:pagination 531-538
    22 schema:productId N285d54fe6da940c991cc2663a1272d17
    23 N299eeb6c1769466db866ce957f226733
    24 Ndfc65a7c58f64ed9a28140e828cb5157
    25 schema:publisher N9363ccb3e7e44e9488e8f1dc46e457e6
    26 schema:sameAs https://app.dimensions.ai/details/publication/pub.1109832331
    27 https://doi.org/10.1007/978-3-030-03493-1_55
    28 schema:sdDatePublished 2019-04-16T04:41
    29 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    30 schema:sdPublisher Nbc9e8abc7116485e963b881774a00d50
    31 schema:url https://link.springer.com/10.1007%2F978-3-030-03493-1_55
    32 sgo:license sg:explorer/license/
    33 sgo:sdDataset chapters
    34 rdf:type schema:Chapter
    35 N2439712c11e64437aafc6dd0ae63c134 rdf:first sg:person.010660771606.18
    36 rdf:rest N4703cbeba22b46569f081c7aefa4c455
    37 N285d54fe6da940c991cc2663a1272d17 schema:name readcube_id
    38 schema:value 1277e3d787878f79818b1dcb8047875680de0f3ecf16fc32c94bc42f1a115cda
    39 rdf:type schema:PropertyValue
    40 N299eeb6c1769466db866ce957f226733 schema:name dimensions_id
    41 schema:value pub.1109832331
    42 rdf:type schema:PropertyValue
    43 N4703cbeba22b46569f081c7aefa4c455 rdf:first sg:person.014640541614.35
    44 rdf:rest Nd4af797211d2486cb594383ab6794f91
    45 N498992f0297b406381f8234cef673c73 rdf:first N5fd8fc53245546d0bbaecd9e16d6c168
    46 rdf:rest Nbd91c70661f04d16916b0d61c11b6a4a
    47 N50ae2502dbb843d99c1683d2847a2921 schema:familyName Tallón-Ballesteros
    48 schema:givenName Antonio J.
    49 rdf:type schema:Person
    50 N58b23636faa44ecfa2ac90f6dd1a6f11 rdf:first sg:person.07662217004.56
    51 rdf:rest rdf:nil
    52 N5c672b67b6bd44eea8046585de4b4b6b schema:familyName Camacho
    53 schema:givenName David
    54 rdf:type schema:Person
    55 N5fd8fc53245546d0bbaecd9e16d6c168 schema:familyName Novais
    56 schema:givenName Paulo
    57 rdf:type schema:Person
    58 N7ca8222d645244d4a0722d9fb44fdef2 rdf:first sg:person.010063411206.84
    59 rdf:rest N2439712c11e64437aafc6dd0ae63c134
    60 N863f8605dbaf43cd98c61a7b1c754329 schema:name Integrated Systems Laboratory, Universidad Politécnica de Madrid ETSI Telecomunicación, Av. Complutense 30, 28040, Madrid, Spain
    61 rdf:type schema:Organization
    62 N9363ccb3e7e44e9488e8f1dc46e457e6 schema:location Cham
    63 schema:name Springer International Publishing
    64 rdf:type schema:Organisation
    65 Nb7be9fa38a3848a2a9b7418ec4911cfb schema:familyName Yin
    66 schema:givenName Hujun
    67 rdf:type schema:Person
    68 Nbc9e8abc7116485e963b881774a00d50 schema:name Springer Nature - SN SciGraph project
    69 rdf:type schema:Organization
    70 Nbd91c70661f04d16916b0d61c11b6a4a rdf:first N50ae2502dbb843d99c1683d2847a2921
    71 rdf:rest rdf:nil
    72 Nbeddad2ef4ad4f82a73e5af379553f97 rdf:first Nb7be9fa38a3848a2a9b7418ec4911cfb
    73 rdf:rest Nf8d37a06f323413da8a87ecc61fb5da1
    74 Nc4721fde888045fe95087ce14880d632 schema:name Integrated Systems Laboratory, Universidad Politécnica de Madrid ETSI Telecomunicación, Av. Complutense 30, 28040, Madrid, Spain
    75 rdf:type schema:Organization
    76 Ncd99e6896d6747f1ac9b06b0146000f5 schema:isbn 978-3-030-03492-4
    77 978-3-030-03493-1
    78 schema:name Intelligent Data Engineering and Automated Learning – IDEAL 2018
    79 rdf:type schema:Book
    80 Nd4af797211d2486cb594383ab6794f91 rdf:first sg:person.012400766577.71
    81 rdf:rest N58b23636faa44ecfa2ac90f6dd1a6f11
    82 Ndd37e318064b41f49f0ce1528ceca1e8 schema:name Integrated Systems Laboratory, Universidad Politécnica de Madrid ETSI Telecomunicación, Av. Complutense 30, 28040, Madrid, Spain
    83 rdf:type schema:Organization
    84 Ndfc65a7c58f64ed9a28140e828cb5157 schema:name doi
    85 schema:value 10.1007/978-3-030-03493-1_55
    86 rdf:type schema:PropertyValue
    87 Nf8d37a06f323413da8a87ecc61fb5da1 rdf:first N5c672b67b6bd44eea8046585de4b4b6b
    88 rdf:rest N498992f0297b406381f8234cef673c73
    89 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    90 schema:name Information and Computing Sciences
    91 rdf:type schema:DefinedTerm
    92 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    93 schema:name Artificial Intelligence and Image Processing
    94 rdf:type schema:DefinedTerm
    95 sg:person.010063411206.84 schema:affiliation N863f8605dbaf43cd98c61a7b1c754329
    96 schema:familyName Blanco
    97 schema:givenName Roberto
    98 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010063411206.84
    99 rdf:type schema:Person
    100 sg:person.010660771606.18 schema:affiliation Ndd37e318064b41f49f0ce1528ceca1e8
    101 schema:familyName Cilla
    102 schema:givenName Juan J.
    103 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010660771606.18
    104 rdf:type schema:Person
    105 sg:person.012400766577.71 schema:affiliation https://www.grid.ac/institutes/grid.5690.a
    106 schema:familyName Malagón
    107 schema:givenName Pedro
    108 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012400766577.71
    109 rdf:type schema:Person
    110 sg:person.014640541614.35 schema:affiliation Nc4721fde888045fe95087ce14880d632
    111 schema:familyName Briongos
    112 schema:givenName Samira
    113 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014640541614.35
    114 rdf:type schema:Person
    115 sg:person.07662217004.56 schema:affiliation https://www.grid.ac/institutes/grid.5690.a
    116 schema:familyName Moya
    117 schema:givenName José M.
    118 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07662217004.56
    119 rdf:type schema:Person
    120 sg:pub.10.1007/bfb0094814 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044906515
    121 https://doi.org/10.1007/bfb0094814
    122 rdf:type schema:CreativeWork
    123 sg:pub.10.1007/s10115-007-0079-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048430917
    124 https://doi.org/10.1007/s10115-007-0079-1
    125 rdf:type schema:CreativeWork
    126 https://doi.org/10.1016/j.knosys.2016.01.025 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039590089
    127 rdf:type schema:CreativeWork
    128 https://doi.org/10.1016/j.neucom.2012.12.023 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028482516
    129 rdf:type schema:CreativeWork
    130 https://doi.org/10.1080/19393555.2015.1125974 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007650632
    131 rdf:type schema:CreativeWork
    132 https://doi.org/10.1109/milcis.2015.7348942 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094497395
    133 rdf:type schema:CreativeWork
    134 https://doi.org/10.1109/tkde.2008.239 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061661916
    135 rdf:type schema:CreativeWork
    136 https://doi.org/10.2478/v10065-010-0035-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030216055
    137 rdf:type schema:CreativeWork
    138 https://www.grid.ac/institutes/grid.5690.a schema:alternateName Technical University of Madrid
    139 schema:name Center for Computational Simulation, Universidad Politécnica de Madrid, Campus de Montegancedo, 28660, Boadilla del Monte, Madrid, Spain
    140 Integrated Systems Laboratory, Universidad Politécnica de Madrid ETSI Telecomunicación, Av. Complutense 30, 28040, Madrid, Spain
    141 rdf:type schema:Organization
     




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


    ...