| fullrecord |
[{"key": "dc.contributor.advisor", "value": "Lehto, Martti", "language": null, "element": "contributor", "qualifier": "advisor", "schema": "dc"}, {"key": "dc.contributor.author", "value": "Jylh\u00e4, Pekka", "language": null, "element": "contributor", "qualifier": "author", "schema": "dc"}, {"key": "dc.date.accessioned", "value": "2024-05-30T05:37:04Z", "language": null, "element": "date", "qualifier": "accessioned", "schema": "dc"}, {"key": "dc.date.available", "value": "2024-05-30T05:37:04Z", "language": null, "element": "date", "qualifier": "available", "schema": "dc"}, {"key": "dc.date.issued", "value": "2024", "language": null, "element": "date", "qualifier": "issued", "schema": "dc"}, {"key": "dc.identifier.uri", "value": "https://jyx.jyu.fi/handle/123456789/95345", "language": null, "element": "identifier", "qualifier": "uri", "schema": "dc"}, {"key": "dc.description.abstract", "value": "T\u00e4ss\u00e4 pro gradu -tutkielmassa tutkitaan selitett\u00e4vi\u00e4 teko\u00e4lymalleja kyberuhkien havainnoinnissa. Kybertoimintaymp\u00e4rist\u00f6 on jatkuvassa murroksessa hy\u00f6kk\u00e4ysten monimutkaistuessa ja muuttuessa entist\u00e4 vakavimmiksi. Hy\u00f6kk\u00e4yksi\u00e4 toteuttavien uhkatoimijoiden toimintaa pyrit\u00e4\u00e4nkin havaitsemaan mahdollisimman aikaisessa vaiheessa, jotta esimerkiksi arkaluonteisten tietojen varastaminen, kiristyshaittaohjelmien toteuttaminen tai muu vihamielinen toiminta kyett\u00e4isiin proaktiivisesti est\u00e4m\u00e4\u00e4n. Kyberturvallisuuden alalla teko\u00e4ly\u00e4 on otettu laajalti k\u00e4ytt\u00f6\u00f6n erilaisten kone- ja syv\u00e4oppimismallien muodossa. Suurin osa teko\u00e4lymalleista on kuitenkin niin monimutkaisia, ettei niiden toiminta ole l\u00e4pin\u00e4kyv\u00e4\u00e4 tai selitett\u00e4viss\u00e4.\r\nTutkimusteht\u00e4v\u00e4n\u00e4 oli selvitt\u00e4\u00e4, miten selitett\u00e4vi\u00e4 teko\u00e4lymalleja voitaisiin hy\u00f6dynt\u00e4\u00e4 kyberuhkien havainnoinnissa. Lis\u00e4ksi tutkimuksessa pyrittiin l\u00f6yt\u00e4m\u00e4\u00e4n vastauksia, voidaanko selitett\u00e4v\u00e4n teko\u00e4lyn avulla saavuttaa korkeampaa luotettavuutta ja tarkkuutta kyberturvallisuuden ratkaisuissa. Kolmantena tutkimusta tukevana l\u00e4hestymiskulmana on, voisivatko kriittisien infrastruktuurin organisaatiot ja niihin vertautuvat instanssit, joilla on korkeat vaatimukset k\u00e4ytetyille tietoj\u00e4rjestelmille, hy\u00f6ty\u00e4 selitett\u00e4vyydest\u00e4 kyber-turvallisuuden ratkaisuissa. \r\nPro gradu -tutkielman teoreettinen viitekehys koottiin edell\u00e4 mainittujen tutkimuskysymysten n\u00e4k\u00f6kulmasta ja se taustoittaa lukijalle tutkittavaa aihetta ja siihen l\u00e4heisimmin kytkeytyvi\u00e4 aihepiirej\u00e4. Tutkimus toteutettiin kvalitatiivisena tutkimuksena k\u00e4ytt\u00e4en aineistol\u00e4ht\u00f6ist\u00e4 sis\u00e4ll\u00f6nanalyysia. Tutkimusaineistoksi valikoitui kirjallisia dokumentteja sek\u00e4 niiden tueksi yksi asiantuntijahaastattelu. Kirjallinen aineisto koostui alan tieteellisist\u00e4 artikkeleista. Tutkimuksen tarkoituksena oli l\u00f6yt\u00e4\u00e4 ilmi\u00f6it\u00e4 ja merkityksi\u00e4 tutkimuskysymysten ymp\u00e4rilt\u00e4.\r\nSis\u00e4ll\u00f6nanalyysin tuloksina tutkimusaineistoista muodostettiin kolme yhdist\u00e4v\u00e4\u00e4 luokkaa, jotka olivat: \u201dXAI-mallien kysynt\u00e4 ja niiden tuoma vahvistus kyberturvallisuuden teko\u00e4lyratkaisuissa\u201d, \u201dPerinteisten koneoppimismallien l\u00e4hes tavoittamattomiin kasvanut takamatka kilpajuoksussa uusia hy\u00f6kk\u00e4ystyyppej\u00e4 vastaan\u201d sek\u00e4 XAI-mallien tutkimuksen tarpeen kasvu kyberturvallisuuden alalla.\u201d\r\nLopuksi muodostettiin johtop\u00e4\u00e4t\u00f6kset, joiden mukaan selitett\u00e4v\u00e4ll\u00e4 teko\u00e4ly parantaa teko\u00e4lymallin l\u00e4pin\u00e4kyvyytt\u00e4 ja sit\u00e4 kautta luotettavuutta kyberturvallisuuden ratkaisuissa. Luotettavuus liittyy l\u00e4heisesti teko\u00e4lymallien ja niihin kytkeytyvien sidosryhmien v\u00e4lille. Selitett\u00e4v\u00e4n teko\u00e4lyn tutkimukseen kaivataan lis\u00e4ksi vahvaa kontribuutiota sek\u00e4 yrityksilt\u00e4, ett\u00e4 tiedeyhteis\u00f6ilt\u00e4. Havaittiin my\u00f6s, ett\u00e4 tutkimukseen on t\u00e4rke\u00e4\u00e4 liitt\u00e4\u00e4 useita eri tieteen-aloja. \r\n\r\nAsiasanat: selitett\u00e4v\u00e4 teko\u00e4ly, XAI, kyberuhka, havainnointi, black-box, kyberturvallisuus", "language": "fi", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.abstract", "value": "In this master\u00b4s thesis, explainable artificial intelligence models in cyber threat detection are researched. The cyber environment is in a constant state of flux as attacks become more complex and severe. The aim is to detect threat actors as early as possible in order to proactively prevent, for example, the theft of sensitive data, the execution of ransomware or other hostile actions. In the field of cyber security, AI has been widely deployed in the form of various machine and deep learning models. However, most AI models are so complex that their behaviour is not transparent or explainable.\r\nThe objective of this research was to investigate how AI models could be used for the detection of cyber threats. The research also aimed to find answers to the question of whether explainable AI can be used to achieve higher reliability and accuracy in cyber security solutions. A third approach that supports the research is whether critical infrastructure organisations and similar entities with high demands on the information systems they use could benefit from explainability in cybersecurity solutions.\r\nThe theoretical framework of the thesis was assembled from the perspective of the above-mentioned research tasks and provides the reader with a background to the topic under study and its most closely related themes. The research was conducted as a qualitative study using content analysis. The research material consisted of written documents and one interview with an expert of cyber security. The written material consists of scientific articles in the field. The aim of the study was to discover phenomena and meanings around the research questions.\r\nAs a result of the content analysis, three unifying categories were formed: \"The demand for XAI models and the reinforcement they bring to AI solutions for cybersecurity\", \"The almost unreachable growing gap of traditional machine learning models in the race against new types of attacks\" and \"The grow-ing need for research on XAI models in cybersecurity.\"\r\nThe study led to the conclusions that explainable AI improves the transparency of the AI model and thus its reliability in cybersecurity solutions. Reliability is closely related to the relationship between AI models and the stakeholders that are connected to them. However, humans are one of the most important elements in this equation. In addition, research on AI that can be explained requires a strong contribution from both the business and scientific communities. The importance of involving a wide range of disciplines in the research was also identified.\r\n\r\nKeywords: explainable artificial intelligence, XAI, cyber threat, detection, black-box", "language": "en", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Submitted by jyx lomake-julkaisija (jyx-julkaisija.group@korppi.jyu.fi) on 2024-05-30T05:37:04Z\r\nNo. of bitstreams: 0", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Made available in DSpace on 2024-05-30T05:37:04Z (GMT). No. of bitstreams: 0", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.format.extent", "value": "117", "language": null, "element": "format", "qualifier": "extent", "schema": "dc"}, {"key": "dc.format.mimetype", "value": "application/pdf", "language": null, "element": "format", "qualifier": "mimetype", "schema": "dc"}, {"key": "dc.language.iso", "value": "fin", "language": null, "element": "language", "qualifier": "iso", "schema": "dc"}, {"key": "dc.rights", "value": "CC BY 4.0", "language": "en", "element": "rights", "qualifier": null, "schema": "dc"}, {"key": "dc.title", "value": "Selitett\u00e4v\u00e4t teko\u00e4lymallit (XAI) kyberuhkien havainnoinnissa", "language": null, "element": "title", "qualifier": null, "schema": "dc"}, {"key": "dc.type", "value": "master thesis", "language": null, "element": "type", "qualifier": null, "schema": "dc"}, {"key": "dc.identifier.urn", "value": "URN:NBN:fi:jyu-202405304108", "language": null, "element": "identifier", "qualifier": "urn", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Faculty of Information Technology", "language": "en", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Informaatioteknologian tiedekunta", "language": "fi", "element": "contributor", "qualifier": "faculty", "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": "Kyberturvallisuus", "language": "fi", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Cyber Security", "language": "en", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "dc.type.coar", "value": "http://purl.org/coar/resource_type/c_bdcc", "language": null, "element": "type", "qualifier": "coar", "schema": "dc"}, {"key": "dc.rights.copyright", "value": "\u00a9 The Author(s)", "language": null, "element": "rights", "qualifier": "copyright", "schema": "dc"}, {"key": "dc.rights.accesslevel", "value": "openAccess", "language": null, "element": "rights", "qualifier": "accesslevel", "schema": "dc"}, {"key": "dc.type.publication", "value": "masterThesis", "language": null, "element": "type", "qualifier": "publication", "schema": "dc"}, {"key": "dc.format.content", "value": "fulltext", "language": null, "element": "format", "qualifier": "content", "schema": "dc"}, {"key": "dc.rights.url", "value": "https://creativecommons.org/licenses/by/4.0/", "language": null, "element": "rights", "qualifier": "url", "schema": "dc"}]
|