hig.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard-cite-them-right
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • sv-SE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • de-DE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Robustness of a neural network used for image classification: The effect of applying distortions on adversarial examples
Högskolan i Gävle, Akademin för teknik och miljö, Avdelningen för Industriell utveckling, IT och Samhällsbyggnad, Datavetenskap.
2018 (engelsk)Independent thesis Basic level (professional degree), 10 poäng / 15 hpOppgave
Abstract [en]

Powerful classifiers as neural networks have long been used to recognise images; these images might depict objects like animals, people or plain text. Distorted images affect the neural network's ability to recognise them, they might be distorted or changed due to distortions related to the camera.Camera related distortions, and how they affect the accuracy, have previously been explored. Recently, it has been proven that images can be intentionally made harder to recognise, an effect that last even after they have been photographed.Such images are known as adversarial examples.The purpose of this thesis is to evaluate how well a neural network can recognise adversarial examples which are also distorted. To evaluate the network, the adversarial examples are distorted in different ways and thereafter fed to the neural network.Different kinds of distortions (rotation, blur, contrast and skew) were used to distort the examples. For each type and strength of distortion the network's ability to classify was measured.Here, it is shown that all distortions influenced the neural network's ability to recognise images.It is concluded that the type and strength of a distortion are important factors when classifying distorted adversarial examples, but also that some distortions, rotation and skew, are able to keep their characteristic influence on the accuracy, even if they are influenced by other distortions.

sted, utgiver, år, opplag, sider
2018. , s. 25
Emneord [en]
LeNet, Distorted Images, MNIST, Adversarial Examples
HSV kategori
Identifikatorer
URN: urn:nbn:se:hig:diva-26118OAI: oai:DiVA.org:hig-26118DiVA, id: diva2:1181511
Fag / kurs
Computer science
Utdanningsprogram
Högskoleingenjör
Veileder
Examiner
Tilgjengelig fra: 2018-02-09 Laget: 2018-02-08 Sist oppdatert: 2018-02-09bibliografisk kontrollert

Open Access i DiVA

fulltext(585 kB)339 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 585 kBChecksum SHA-512
775e15102dae56d41b3a321199d8403635bd19adae39bd292a4dcc01f572ceccecbbefbe412525630a14573de5241e2d158ab54e6a3385ba30ffb565f9ba5bbc
Type fulltextMimetype application/pdf

Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 339 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

urn-nbn

Altmetric

urn-nbn
Totalt: 290 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard-cite-them-right
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • sv-SE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • de-DE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf