Oppiva tekoäly ja takaovihyökkäykset

Tekoälyä voidaan opettaa havainnoimaan itsenäisesti ja tekemään päätöksiä sen pohjalta. Tämä tutkielma kuvaa tekoälyn ohjattua opettamista ja esittelee tekoälyn opettamiseen liittyviä riskejä, joista pääpainotus on datan myrkyttämiseen liittyvissä takaovihyökkäyksissä. Riskejä on sekä tahattomia ett...

Täydet tiedot

Bibliografiset tiedot
Päätekijä: Suvivirta, Melinda
Muut tekijät: Informaatioteknologian tiedekunta, Faculty of Information Technology, Informaatioteknologia, Information Technology, Jyväskylän yliopisto, University of Jyväskylä
Aineistotyyppi: Kandityö
Kieli:fin
Julkaistu: 2022
Aiheet:
Linkit: https://jyx.jyu.fi/handle/123456789/80918
_version_ 1826225799995326464
author Suvivirta, Melinda
author2 Informaatioteknologian tiedekunta Faculty of Information Technology Informaatioteknologia Information Technology Jyväskylän yliopisto University of Jyväskylä
author_facet Suvivirta, Melinda Informaatioteknologian tiedekunta Faculty of Information Technology Informaatioteknologia Information Technology Jyväskylän yliopisto University of Jyväskylä Suvivirta, Melinda Informaatioteknologian tiedekunta Faculty of Information Technology Informaatioteknologia Information Technology Jyväskylän yliopisto University of Jyväskylä
author_sort Suvivirta, Melinda
datasource_str_mv jyx
description Tekoälyä voidaan opettaa havainnoimaan itsenäisesti ja tekemään päätöksiä sen pohjalta. Tämä tutkielma kuvaa tekoälyn ohjattua opettamista ja esittelee tekoälyn opettamiseen liittyviä riskejä, joista pääpainotus on datan myrkyttämiseen liittyvissä takaovihyökkäyksissä. Riskejä on sekä tahattomia että tahallisia, mutta yhteistä niille on, että ne pohjautuvat vahvasti siihen, millaisella datalla tekoälyä opetetaan. Takaovihyökkäykset luovat vakavan uhan monille tekoälyohjelmille ja niiden tunnistaminen on usein haastavaa. AI can be teached to make observations and then make independent choices based on them. This thesis describes supervised learning of AI and undergoes different risks that are involved with teaching AI. The main focus is on backdoor attacks that are involved with data poisoning. There are both unintentional and intentional risks associated with teaching AI. The risks are mainly based on what kind of data the AI is being taught with. Backdoor attacks create a serious threat to several AI programs and it is often difficult to detect them.
first_indexed 2022-05-06T20:00:36Z
format Kandityö
free_online_boolean 1
fullrecord [{"key": "dc.contributor.advisor", "value": "Tiihonen, Timo", "language": "", "element": "contributor", "qualifier": "advisor", "schema": "dc"}, {"key": "dc.contributor.author", "value": "Suvivirta, Melinda", "language": "", "element": "contributor", "qualifier": "author", "schema": "dc"}, {"key": "dc.date.accessioned", "value": "2022-05-06T05:49:08Z", "language": null, "element": "date", "qualifier": "accessioned", "schema": "dc"}, {"key": "dc.date.available", "value": "2022-05-06T05:49:08Z", "language": null, "element": "date", "qualifier": "available", "schema": "dc"}, {"key": "dc.date.issued", "value": "2022", "language": "", "element": "date", "qualifier": "issued", "schema": "dc"}, {"key": "dc.identifier.uri", "value": "https://jyx.jyu.fi/handle/123456789/80918", "language": null, "element": "identifier", "qualifier": "uri", "schema": "dc"}, {"key": "dc.description.abstract", "value": "Teko\u00e4ly\u00e4 voidaan opettaa havainnoimaan itsen\u00e4isesti ja tekem\u00e4\u00e4n p\u00e4\u00e4t\u00f6ksi\u00e4 sen pohjalta. T\u00e4m\u00e4 tutkielma kuvaa teko\u00e4lyn ohjattua opettamista ja esittelee teko\u00e4lyn opettamiseen liittyvi\u00e4 riskej\u00e4, joista p\u00e4\u00e4painotus on datan myrkytt\u00e4miseen liittyviss\u00e4 takaovihy\u00f6kk\u00e4yksiss\u00e4. Riskej\u00e4 on sek\u00e4 tahattomia ett\u00e4 tahallisia, mutta yhteist\u00e4 niille on, ett\u00e4 ne pohjautuvat vahvasti siihen, millaisella datalla teko\u00e4ly\u00e4 opetetaan. Takaovihy\u00f6kk\u00e4ykset luovat vakavan uhan monille teko\u00e4lyohjelmille ja niiden tunnistaminen on usein haastavaa.", "language": "fi", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.abstract", "value": "AI can be teached to make observations and then make independent choices based on them. This thesis describes supervised learning of AI and undergoes different risks that are involved with teaching AI. The main focus is on backdoor attacks that are involved with data poisoning. There are both unintentional and intentional risks associated with teaching AI. The risks are mainly based on what kind of data the AI is being taught with. Backdoor attacks create a serious threat to several AI programs and it is often difficult to detect them.", "language": "en", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Submitted by Paivi Vuorio (paelvuor@jyu.fi) on 2022-05-06T05:49:08Z\nNo. of bitstreams: 0", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Made available in DSpace on 2022-05-06T05:49:08Z (GMT). No. of bitstreams: 0\n Previous issue date: 2022", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.format.extent", "value": "28", "language": "", "element": "format", "qualifier": "extent", "schema": "dc"}, {"key": "dc.language.iso", "value": "fin", "language": null, "element": "language", "qualifier": "iso", "schema": "dc"}, {"key": "dc.rights", "value": "In Copyright", "language": "en", "element": "rights", "qualifier": null, "schema": "dc"}, {"key": "dc.subject.other", "value": "datan myrkytys", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "takaovihy\u00f6kk\u00e4ykset", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.title", "value": "Oppiva teko\u00e4ly ja takaovihy\u00f6kk\u00e4ykset", "language": "", "element": "title", "qualifier": null, "schema": "dc"}, {"key": "dc.type", "value": "bachelor thesis", "language": null, "element": "type", "qualifier": null, "schema": "dc"}, {"key": "dc.identifier.urn", "value": "URN:NBN:fi:jyu-202205062571", "language": "", "element": "identifier", "qualifier": "urn", "schema": "dc"}, {"key": "dc.type.ontasot", "value": "Bachelor's thesis", "language": "en", "element": "type", "qualifier": "ontasot", "schema": "dc"}, {"key": "dc.type.ontasot", "value": "Kandidaatinty\u00f6", "language": "fi", "element": "type", "qualifier": "ontasot", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Informaatioteknologian tiedekunta", "language": "fi", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Faculty of Information Technology", "language": "en", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.department", "value": "Informaatioteknologia", "language": "fi", "element": "contributor", "qualifier": "department", "schema": "dc"}, {"key": "dc.contributor.department", "value": "Information Technology", "language": "en", "element": "contributor", "qualifier": "department", "schema": "dc"}, {"key": "dc.contributor.organization", "value": "Jyv\u00e4skyl\u00e4n yliopisto", "language": "fi", "element": "contributor", "qualifier": "organization", "schema": "dc"}, {"key": "dc.contributor.organization", "value": "University of Jyv\u00e4skyl\u00e4", "language": "en", "element": "contributor", "qualifier": "organization", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Tietotekniikka", "language": "fi", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Mathematical Information Technology", "language": "en", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "yvv.contractresearch.funding", "value": "0", "language": "", "element": "contractresearch", "qualifier": "funding", "schema": "yvv"}, {"key": "dc.type.coar", "value": "http://purl.org/coar/resource_type/c_7a1f", "language": null, "element": "type", "qualifier": "coar", "schema": "dc"}, {"key": "dc.rights.accesslevel", "value": "openAccess", "language": null, "element": "rights", "qualifier": "accesslevel", "schema": "dc"}, {"key": "dc.type.publication", "value": "bachelorThesis", "language": null, "element": "type", "qualifier": "publication", "schema": "dc"}, {"key": "dc.subject.oppiainekoodi", "value": "602", "language": "", "element": "subject", "qualifier": "oppiainekoodi", "schema": "dc"}, {"key": "dc.subject.yso", "value": "teko\u00e4ly", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "koneoppiminen", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "tietotekniikka", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.rights.url", "value": "https://rightsstatements.org/page/InC/1.0/", "language": null, "element": "rights", "qualifier": "url", "schema": "dc"}]
id jyx.123456789_80918
language fin
last_indexed 2025-02-18T10:56:06Z
main_date 2022-01-01T00:00:00Z
main_date_str 2022
online_boolean 1
online_urls_str_mv {"url":"https:\/\/jyx.jyu.fi\/bitstreams\/0f576422-6022-48c9-a9d2-856b636acda8\/download","text":"URN:NBN:fi:jyu-202205062571.pdf","source":"jyx","mediaType":"application\/pdf"}
publishDate 2022
record_format qdc
source_str_mv jyx
spellingShingle Suvivirta, Melinda Oppiva tekoäly ja takaovihyökkäykset datan myrkytys takaovihyökkäykset Tietotekniikka Mathematical Information Technology 602 tekoäly koneoppiminen tietotekniikka
title Oppiva tekoäly ja takaovihyökkäykset
title_full Oppiva tekoäly ja takaovihyökkäykset
title_fullStr Oppiva tekoäly ja takaovihyökkäykset Oppiva tekoäly ja takaovihyökkäykset
title_full_unstemmed Oppiva tekoäly ja takaovihyökkäykset Oppiva tekoäly ja takaovihyökkäykset
title_short Oppiva tekoäly ja takaovihyökkäykset
title_sort oppiva tekoäly ja takaovihyökkäykset
title_txtP Oppiva tekoäly ja takaovihyökkäykset
topic datan myrkytys takaovihyökkäykset Tietotekniikka Mathematical Information Technology 602 tekoäly koneoppiminen tietotekniikka
topic_facet 602 Mathematical Information Technology Tietotekniikka datan myrkytys koneoppiminen takaovihyökkäykset tekoäly tietotekniikka
url https://jyx.jyu.fi/handle/123456789/80918 http://www.urn.fi/URN:NBN:fi:jyu-202205062571
work_keys_str_mv AT suvivirtamelinda oppivatekoälyjatakaovihyökkäykset