The Security of Machine Learning Systems View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2018-09-18

AUTHORS

Luis Muñoz-González , Emil C. Lupu

ABSTRACT

Machine learning lies at the core of many modern applications, extracting valuable information from data acquired from numerous sources. It has produced a disruptive change in society, providing new functionality, improved quality of life for users, e.g., through personalization, optimized use of resources, and the automation of many processes. However, machine learning systems can themselves be the targets of attackers, who might gain a significant advantage by exploiting the vulnerabilities of learning algorithms. Such attacks have already been reported in the wild in different application domains. This chapter describes the mechanisms that allow attackers to compromise machine learning systems by injecting malicious data or exploiting the algorithms’ weaknesses and blind spots. Furthermore, mechanisms that can help mitigate the effect of such attacks are also explained, along with the challenges of designing more secure machine learning systems. More... »

PAGES

47-79

Book

TITLE

AI in Cybersecurity

ISBN

978-3-319-98841-2
978-3-319-98842-9

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-98842-9_3

DOI

http://dx.doi.org/10.1007/978-3-319-98842-9_3

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1107054572


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/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "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"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Imperial College London, London, UK", 
          "id": "http://www.grid.ac/institutes/grid.7445.2", 
          "name": [
            "Imperial College London, London, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Mu\u00f1oz-Gonz\u00e1lez", 
        "givenName": "Luis", 
        "id": "sg:person.011755172717.81", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011755172717.81"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Imperial College London, London, UK", 
          "id": "http://www.grid.ac/institutes/grid.7445.2", 
          "name": [
            "Imperial College London, London, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lupu", 
        "givenName": "Emil C.", 
        "id": "sg:person.013404167044.28", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013404167044.28"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2018-09-18", 
    "datePublishedReg": "2018-09-18", 
    "description": "Machine learning lies at the core of many modern applications, extracting valuable information from data acquired from numerous sources. It has produced a disruptive change in society, providing new functionality, improved quality of life for users, e.g., through personalization, optimized use of resources, and the automation of many processes. However, machine learning systems can themselves be the targets of attackers, who might gain a significant advantage by exploiting the vulnerabilities of learning algorithms. Such attacks have already been reported in the wild in different application domains. This chapter describes the mechanisms that allow attackers to compromise machine learning systems by injecting malicious data or exploiting the algorithms\u2019 weaknesses and blind spots. Furthermore, mechanisms that can help mitigate the effect of such attacks are also explained, along with the challenges of designing more secure machine learning systems.", 
    "editor": [
      {
        "familyName": "Sikos", 
        "givenName": "Leslie F.", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-98842-9_3", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-319-98841-2", 
        "978-3-319-98842-9"
      ], 
      "name": "AI in Cybersecurity", 
      "type": "Book"
    }, 
    "keywords": [
      "Machine Learning Systems", 
      "such attacks", 
      "learning system", 
      "target of attackers", 
      "different application domains", 
      "secure machine", 
      "malicious data", 
      "application domains", 
      "machine learning", 
      "algorithm weakness", 
      "modern applications", 
      "new functionalities", 
      "attacker", 
      "machine", 
      "use of resources", 
      "disruptive changes", 
      "attacks", 
      "users", 
      "automation", 
      "personalization", 
      "system", 
      "security", 
      "significant advantages", 
      "algorithm", 
      "numerous sources", 
      "valuable information", 
      "learning", 
      "blind spots", 
      "functionality", 
      "information", 
      "resources", 
      "data", 
      "applications", 
      "weakness", 
      "challenges", 
      "vulnerability", 
      "domain", 
      "advantages", 
      "quality", 
      "wild", 
      "process", 
      "use", 
      "core", 
      "chapter", 
      "mechanism", 
      "source", 
      "spots", 
      "target", 
      "society", 
      "life", 
      "changes", 
      "quality of life", 
      "effect"
    ], 
    "name": "The Security of Machine Learning Systems", 
    "pagination": "47-79", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1107054572"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-98842-9_3"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-98842-9_3", 
      "https://app.dimensions.ai/details/publication/pub.1107054572"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-09-02T16:10", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220902/entities/gbq_results/chapter/chapter_138.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-98842-9_3"
  }
]
 

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.10.1007/978-3-319-98842-9_3'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-98842-9_3'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-98842-9_3'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-98842-9_3'


 

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

119 TRIPLES      22 PREDICATES      76 URIs      69 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-98842-9_3 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nc468af3a30774a51b7df86886e3190be
4 schema:datePublished 2018-09-18
5 schema:datePublishedReg 2018-09-18
6 schema:description Machine learning lies at the core of many modern applications, extracting valuable information from data acquired from numerous sources. It has produced a disruptive change in society, providing new functionality, improved quality of life for users, e.g., through personalization, optimized use of resources, and the automation of many processes. However, machine learning systems can themselves be the targets of attackers, who might gain a significant advantage by exploiting the vulnerabilities of learning algorithms. Such attacks have already been reported in the wild in different application domains. This chapter describes the mechanisms that allow attackers to compromise machine learning systems by injecting malicious data or exploiting the algorithms’ weaknesses and blind spots. Furthermore, mechanisms that can help mitigate the effect of such attacks are also explained, along with the challenges of designing more secure machine learning systems.
7 schema:editor N18bc080fd45c48fc9ce1121034dc2eb6
8 schema:genre chapter
9 schema:isAccessibleForFree true
10 schema:isPartOf N960be2a6fb3344eda8033ede9711be21
11 schema:keywords Machine Learning Systems
12 advantages
13 algorithm
14 algorithm weakness
15 application domains
16 applications
17 attacker
18 attacks
19 automation
20 blind spots
21 challenges
22 changes
23 chapter
24 core
25 data
26 different application domains
27 disruptive changes
28 domain
29 effect
30 functionality
31 information
32 learning
33 learning system
34 life
35 machine
36 machine learning
37 malicious data
38 mechanism
39 modern applications
40 new functionalities
41 numerous sources
42 personalization
43 process
44 quality
45 quality of life
46 resources
47 secure machine
48 security
49 significant advantages
50 society
51 source
52 spots
53 such attacks
54 system
55 target
56 target of attackers
57 use
58 use of resources
59 users
60 valuable information
61 vulnerability
62 weakness
63 wild
64 schema:name The Security of Machine Learning Systems
65 schema:pagination 47-79
66 schema:productId N53168399ece44d188124f749b917c65a
67 N7b48360250664679a28989e4f5022bb9
68 schema:publisher N67c5743671764dd7811f168cede20850
69 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107054572
70 https://doi.org/10.1007/978-3-319-98842-9_3
71 schema:sdDatePublished 2022-09-02T16:10
72 schema:sdLicense https://scigraph.springernature.com/explorer/license/
73 schema:sdPublisher N6cc29971040a4def8b6bd3c111e489fb
74 schema:url https://doi.org/10.1007/978-3-319-98842-9_3
75 sgo:license sg:explorer/license/
76 sgo:sdDataset chapters
77 rdf:type schema:Chapter
78 N18bc080fd45c48fc9ce1121034dc2eb6 rdf:first N3f09477e93c9426888433b7a6dd14eff
79 rdf:rest rdf:nil
80 N3f09477e93c9426888433b7a6dd14eff schema:familyName Sikos
81 schema:givenName Leslie F.
82 rdf:type schema:Person
83 N53168399ece44d188124f749b917c65a schema:name dimensions_id
84 schema:value pub.1107054572
85 rdf:type schema:PropertyValue
86 N67c5743671764dd7811f168cede20850 schema:name Springer Nature
87 rdf:type schema:Organisation
88 N6cc29971040a4def8b6bd3c111e489fb schema:name Springer Nature - SN SciGraph project
89 rdf:type schema:Organization
90 N7b48360250664679a28989e4f5022bb9 schema:name doi
91 schema:value 10.1007/978-3-319-98842-9_3
92 rdf:type schema:PropertyValue
93 N960be2a6fb3344eda8033ede9711be21 schema:isbn 978-3-319-98841-2
94 978-3-319-98842-9
95 schema:name AI in Cybersecurity
96 rdf:type schema:Book
97 Nad249ff783dd4c25b24c52c5483a96d7 rdf:first sg:person.013404167044.28
98 rdf:rest rdf:nil
99 Nc468af3a30774a51b7df86886e3190be rdf:first sg:person.011755172717.81
100 rdf:rest Nad249ff783dd4c25b24c52c5483a96d7
101 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
102 schema:name Information and Computing Sciences
103 rdf:type schema:DefinedTerm
104 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
105 schema:name Artificial Intelligence and Image Processing
106 rdf:type schema:DefinedTerm
107 sg:person.011755172717.81 schema:affiliation grid-institutes:grid.7445.2
108 schema:familyName Muñoz-González
109 schema:givenName Luis
110 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011755172717.81
111 rdf:type schema:Person
112 sg:person.013404167044.28 schema:affiliation grid-institutes:grid.7445.2
113 schema:familyName Lupu
114 schema:givenName Emil C.
115 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013404167044.28
116 rdf:type schema:Person
117 grid-institutes:grid.7445.2 schema:alternateName Imperial College London, London, UK
118 schema:name Imperial College London, London, UK
119 rdf:type schema:Organization
 




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


...