Backdoors: Definition, Deniability and Detection View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2018-09-07

AUTHORS

Sam L. Thomas , Aurélien Francillon

ABSTRACT

Detecting backdoors is a difficult task; automating that detection process is equally challenging. Evidence for these claims lie in both the lack of automated tooling, and the fact that the vast majority of real-world backdoors are still detected by labourious manual analysis. The term backdoor, casually used in both the literature and the media, does not have a concrete or rigorous definition. In this work we provide such a definition. Further, we present a framework for reasoning about backdoors through four key components, which allows them to be modelled succinctly and provides a means of rigorously defining the process of their detection. Moreover, we introduce the notion of deniability in regard to backdoor implementations which permits reasoning about the attribution and accountability of backdoor implementers. We show our framework is able to model eleven, diverse, real-world backdoors, and one, more complex backdoor from the literature, and, in doing so, provides a means to reason about how they can be detected and their deniability. Further, we demonstrate how our framework can be used to decompose backdoor detection methodologies, which serves as a basis for developing future backdoor detection tools, and shows how current state-of-the-art approaches consider neither a sound nor complete model. More... »

PAGES

92-113

Book

TITLE

Research in Attacks, Intrusions, and Defenses

ISBN

978-3-030-00469-9
978-3-030-00470-5

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-030-00470-5_5

DOI

http://dx.doi.org/10.1007/978-3-030-00470-5_5

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1106836614


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": "University of Birmingham, Birmingham, UK", 
          "id": "http://www.grid.ac/institutes/grid.6572.6", 
          "name": [
            "Univ Rennes, CNRS, IRISA, Rennes, France", 
            "University of Birmingham, Birmingham, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Thomas", 
        "givenName": "Sam L.", 
        "id": "sg:person.015540220040.15", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015540220040.15"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "EURECOM, Biot, France", 
          "id": "http://www.grid.ac/institutes/grid.28848.3e", 
          "name": [
            "EURECOM, Biot, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Francillon", 
        "givenName": "Aur\u00e9lien", 
        "id": "sg:person.015103646733.70", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015103646733.70"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2018-09-07", 
    "datePublishedReg": "2018-09-07", 
    "description": "Detecting backdoors is a difficult task; automating that detection process is equally challenging. Evidence for these claims lie in both the lack of automated tooling, and the fact that the vast majority of real-world backdoors are still detected by labourious manual analysis. The term backdoor, casually used in both the literature and the media, does not have a concrete or rigorous definition. In this work we provide such a definition. Further, we present a framework for reasoning about backdoors through four key components, which allows them to be modelled succinctly and provides a means of rigorously defining the process of their detection. Moreover, we introduce the notion of deniability in regard to backdoor implementations which permits reasoning about the attribution and accountability of backdoor implementers. We show our framework is able to model eleven, diverse, real-world backdoors, and one, more complex backdoor from the literature, and, in doing so, provides a means to reason about how they can be detected and their deniability. Further, we demonstrate how our framework can be used to decompose backdoor detection methodologies, which serves as a basis for developing future backdoor detection tools, and shows how current state-of-the-art approaches consider neither a sound nor complete model.", 
    "editor": [
      {
        "familyName": "Bailey", 
        "givenName": "Michael", 
        "type": "Person"
      }, 
      {
        "familyName": "Holz", 
        "givenName": "Thorsten", 
        "type": "Person"
      }, 
      {
        "familyName": "Stamatogiannakis", 
        "givenName": "Manolis", 
        "type": "Person"
      }, 
      {
        "familyName": "Ioannidis", 
        "givenName": "Sotiris", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-030-00470-5_5", 
    "inLanguage": "en", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-030-00469-9", 
        "978-3-030-00470-5"
      ], 
      "name": "Research in Attacks, Intrusions, and Defenses", 
      "type": "Book"
    }, 
    "keywords": [
      "notion of deniability", 
      "art approaches", 
      "backdoor", 
      "manual analysis", 
      "detection process", 
      "deniability", 
      "detection tools", 
      "difficult task", 
      "detection methodology", 
      "framework", 
      "current state", 
      "complete model", 
      "rigorous definition", 
      "task", 
      "key component", 
      "detection", 
      "implementation", 
      "definition", 
      "tooling", 
      "tool", 
      "implementers", 
      "methodology", 
      "process", 
      "work", 
      "means", 
      "model", 
      "notion", 
      "literature", 
      "components", 
      "state", 
      "vast majority", 
      "fact", 
      "lack", 
      "basis", 
      "accountability", 
      "analysis", 
      "regard", 
      "attribution", 
      "medium", 
      "claims", 
      "majority", 
      "evidence", 
      "approach", 
      "real-world backdoors", 
      "labourious manual analysis", 
      "term backdoor", 
      "backdoor implementations", 
      "backdoor implementers", 
      "complex backdoor", 
      "backdoor detection methodologies", 
      "future backdoor detection tools", 
      "backdoor detection tools"
    ], 
    "name": "Backdoors: Definition, Deniability and Detection", 
    "pagination": "92-113", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1106836614"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-030-00470-5_5"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-030-00470-5_5", 
      "https://app.dimensions.ai/details/publication/pub.1106836614"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2021-12-01T20:06", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20211201/entities/gbq_results/chapter/chapter_340.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-030-00470-5_5"
  }
]
 

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.10.1007/978-3-030-00470-5_5'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-00470-5_5'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-00470-5_5'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-00470-5_5'


 

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

138 TRIPLES      23 PREDICATES      77 URIs      70 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-030-00470-5_5 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N990927282cd04720bd6be4a40408b94f
4 schema:datePublished 2018-09-07
5 schema:datePublishedReg 2018-09-07
6 schema:description Detecting backdoors is a difficult task; automating that detection process is equally challenging. Evidence for these claims lie in both the lack of automated tooling, and the fact that the vast majority of real-world backdoors are still detected by labourious manual analysis. The term backdoor, casually used in both the literature and the media, does not have a concrete or rigorous definition. In this work we provide such a definition. Further, we present a framework for reasoning about backdoors through four key components, which allows them to be modelled succinctly and provides a means of rigorously defining the process of their detection. Moreover, we introduce the notion of deniability in regard to backdoor implementations which permits reasoning about the attribution and accountability of backdoor implementers. We show our framework is able to model eleven, diverse, real-world backdoors, and one, more complex backdoor from the literature, and, in doing so, provides a means to reason about how they can be detected and their deniability. Further, we demonstrate how our framework can be used to decompose backdoor detection methodologies, which serves as a basis for developing future backdoor detection tools, and shows how current state-of-the-art approaches consider neither a sound nor complete model.
7 schema:editor N715bb561e4f64fc59b04467261702709
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree true
11 schema:isPartOf N7292426d79a848dba7290683f769def3
12 schema:keywords accountability
13 analysis
14 approach
15 art approaches
16 attribution
17 backdoor
18 backdoor detection methodologies
19 backdoor detection tools
20 backdoor implementations
21 backdoor implementers
22 basis
23 claims
24 complete model
25 complex backdoor
26 components
27 current state
28 definition
29 deniability
30 detection
31 detection methodology
32 detection process
33 detection tools
34 difficult task
35 evidence
36 fact
37 framework
38 future backdoor detection tools
39 implementation
40 implementers
41 key component
42 labourious manual analysis
43 lack
44 literature
45 majority
46 manual analysis
47 means
48 medium
49 methodology
50 model
51 notion
52 notion of deniability
53 process
54 real-world backdoors
55 regard
56 rigorous definition
57 state
58 task
59 term backdoor
60 tool
61 tooling
62 vast majority
63 work
64 schema:name Backdoors: Definition, Deniability and Detection
65 schema:pagination 92-113
66 schema:productId N33a621a4490444e8baece0a2c89d7a72
67 N43a4fb566cdb4f5e896a34340865bd29
68 schema:publisher N2ef7e364d88b43e68ad68dfc6da08288
69 schema:sameAs https://app.dimensions.ai/details/publication/pub.1106836614
70 https://doi.org/10.1007/978-3-030-00470-5_5
71 schema:sdDatePublished 2021-12-01T20:06
72 schema:sdLicense https://scigraph.springernature.com/explorer/license/
73 schema:sdPublisher N5c3e7c4752f0411785bfff47d82985a8
74 schema:url https://doi.org/10.1007/978-3-030-00470-5_5
75 sgo:license sg:explorer/license/
76 sgo:sdDataset chapters
77 rdf:type schema:Chapter
78 N195f7fe79c4c402f8a353b2c23f3c153 rdf:first sg:person.015103646733.70
79 rdf:rest rdf:nil
80 N1a703bf62a644767b28bac1a92f4e5c5 schema:familyName Holz
81 schema:givenName Thorsten
82 rdf:type schema:Person
83 N2ef7e364d88b43e68ad68dfc6da08288 schema:name Springer Nature
84 rdf:type schema:Organisation
85 N33a621a4490444e8baece0a2c89d7a72 schema:name doi
86 schema:value 10.1007/978-3-030-00470-5_5
87 rdf:type schema:PropertyValue
88 N43a4fb566cdb4f5e896a34340865bd29 schema:name dimensions_id
89 schema:value pub.1106836614
90 rdf:type schema:PropertyValue
91 N5c3e7c4752f0411785bfff47d82985a8 schema:name Springer Nature - SN SciGraph project
92 rdf:type schema:Organization
93 N715bb561e4f64fc59b04467261702709 rdf:first N9405e0ac7ddf4dff8d3e1180f250ff4e
94 rdf:rest Ne563bece2f934f1ba2403fa1a56c3f85
95 N7292426d79a848dba7290683f769def3 schema:isbn 978-3-030-00469-9
96 978-3-030-00470-5
97 schema:name Research in Attacks, Intrusions, and Defenses
98 rdf:type schema:Book
99 N9405e0ac7ddf4dff8d3e1180f250ff4e schema:familyName Bailey
100 schema:givenName Michael
101 rdf:type schema:Person
102 N990927282cd04720bd6be4a40408b94f rdf:first sg:person.015540220040.15
103 rdf:rest N195f7fe79c4c402f8a353b2c23f3c153
104 Nc32594a3e969403e9dc0a8937bb83edb schema:familyName Stamatogiannakis
105 schema:givenName Manolis
106 rdf:type schema:Person
107 Nc946154e66bb4b8e9ad3dddcfdec103c schema:familyName Ioannidis
108 schema:givenName Sotiris
109 rdf:type schema:Person
110 Ne22ce0b043114a3d8ecc0bd2278f2f16 rdf:first Nc946154e66bb4b8e9ad3dddcfdec103c
111 rdf:rest rdf:nil
112 Ne563bece2f934f1ba2403fa1a56c3f85 rdf:first N1a703bf62a644767b28bac1a92f4e5c5
113 rdf:rest Nfef2cd82063e4f748094dd326246da21
114 Nfef2cd82063e4f748094dd326246da21 rdf:first Nc32594a3e969403e9dc0a8937bb83edb
115 rdf:rest Ne22ce0b043114a3d8ecc0bd2278f2f16
116 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
117 schema:name Information and Computing Sciences
118 rdf:type schema:DefinedTerm
119 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
120 schema:name Artificial Intelligence and Image Processing
121 rdf:type schema:DefinedTerm
122 sg:person.015103646733.70 schema:affiliation grid-institutes:grid.28848.3e
123 schema:familyName Francillon
124 schema:givenName Aurélien
125 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015103646733.70
126 rdf:type schema:Person
127 sg:person.015540220040.15 schema:affiliation grid-institutes:grid.6572.6
128 schema:familyName Thomas
129 schema:givenName Sam L.
130 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015540220040.15
131 rdf:type schema:Person
132 grid-institutes:grid.28848.3e schema:alternateName EURECOM, Biot, France
133 schema:name EURECOM, Biot, France
134 rdf:type schema:Organization
135 grid-institutes:grid.6572.6 schema:alternateName University of Birmingham, Birmingham, UK
136 schema:name Univ Rennes, CNRS, IRISA, Rennes, France
137 University of Birmingham, Birmingham, UK
138 rdf:type schema:Organization
 




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


...