| fullrecord |
[{"key": "dc.contributor.advisor", "value": "Costin, Andrei", "language": "", "element": "contributor", "qualifier": "advisor", "schema": "dc"}, {"key": "dc.contributor.author", "value": "Jormakka, Ossi", "language": "", "element": "contributor", "qualifier": "author", "schema": "dc"}, {"key": "dc.date.accessioned", "value": "2019-11-06T06:51:08Z", "language": null, "element": "date", "qualifier": "accessioned", "schema": "dc"}, {"key": "dc.date.available", "value": "2019-11-06T06:51:08Z", "language": null, "element": "date", "qualifier": "available", "schema": "dc"}, {"key": "dc.date.issued", "value": "2019", "language": "", "element": "date", "qualifier": "issued", "schema": "dc"}, {"key": "dc.identifier.uri", "value": "https://jyx.jyu.fi/handle/123456789/66196", "language": null, "element": "identifier", "qualifier": "uri", "schema": "dc"}, {"key": "dc.description.abstract", "value": "Automatisoitu haavoittuvuuksien etsiminen ja haavoittuvuuksien yksityiskohtien ennustaminen voi auttaa asiantuntijoita priorisoimaan ohjelmistovirheit\u00e4,\njoka voi johtaa nopeampaan virheenkorjaukseen. T\u00e4ss\u00e4 ty\u00f6ss\u00e4 k\u00e4ytettiin National Vulnerability Database -tietokantaa tutkittaessa kuinka haavoittuvuuskuvauksien perusteella voidaan havaita haavoittuvuuksia mist\u00e4 tahansa tekstist\u00e4\nsek\u00e4 ennustaa haavoittuvuuksien vakavuus ja haavoittuvuustyyppi. Common\nVulnerability Scoring System -j\u00e4rjestelm\u00e4 tarjoaa tavan mitata haavoittuvuuksien vakavuuksia. Common Weakness Enumeration -j\u00e4rjestelm\u00e4 tarjoaa hierarkkisen luokittelun yleisiin haavoittuvuustyyppeihin. Olemassa olevat tutkimukset haavoittuvuuksien tekstiluokittelussa usein rajoittuvat kapeaan alueeseen,\nesimerkiksi vain johonkin Common Vulnerability Scoring System -j\u00e4rjestelm\u00e4n\nversioon. T\u00e4m\u00e4 ty\u00f6 antaa yleiskuvan virheraporttien luokittelusta sek\u00e4 vakavuuden ja haavoittuvuustyypin ennustamisesta. Ty\u00f6ss\u00e4 pyrittiin k\u00e4ytt\u00e4m\u00e4\u00e4n laajasti\ntunnettuja tekstin esik\u00e4sittelymenetelmi\u00e4 sek\u00e4 monia muita Scikit-learn -kirjaston tarjoamia luonnollisen tekstin k\u00e4sittelyn vaihtoehtoja ja koneoppimismenetelmi\u00e4.\nTulokset osoittavat 2-grammin avainsanapohjaisen menetelm\u00e4n olevan\nyht\u00e4 tehokas kuin yhden luokan tukivektorikone kun esik\u00e4sittelyn\u00e4 k\u00e4ytet\u00e4\u00e4n\nTerm Frequency \u2013 Inverse Document Frequency -painotusta ja sanojen taivutusmuotojen muuttamista perusmuotoon (lemmatizing). Haavoittuvuuksien vakavuuden ennustamisessa saadaan parempia tuloksia Common Vulnerability Scoring System -j\u00e4rjestelm\u00e4n versiolle 2 kuin j\u00e4rjestelm\u00e4n versiolle 3. Lineaarinen\ntukivekorikone saavutti korkeimman F1-tuloksen haavoittuvuuksien vakavuuden ja haavoittuvuustyypin luokittelussa. Lis\u00e4ksi t\u00e4ss\u00e4 ty\u00f6ss\u00e4 on yhteenveto uusimpaan National Vulnerability Database -tietokannan tietoon.", "language": "fi", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.abstract", "value": "Automated vulnerability detection and prediction of vulnerability details may\nhelp security specialists to prioritize bug reports and getting earlier fixes to\nsecurity related software defects. This thesis is about finding vulnerable-like\ndescriptions from any text and classifying vulnerability severities and weakness\ntypes. Vulnerability severities are measured using Common Vulnerability\nScoring System. Common Weakness Enumeration is a hierarchical list of\nweakness types that each vulnerability can be classified to. The scoring and\nweakness type information for known vulnerabilities are available on National\nVulnerability Database. Many existing research about vulnerability text-only\nclassification is limited to a narrow area, for example, specific version of\nCommon Vulnerability Scoring System. This thesis gives an overview of\nclassifying bug reports with severities and weakness types altogether. The Scikitlearn library\u2019s interfaces were used extensively to implement text preprocessing,\nmachine learning classification, and experiment validation. Experiments include\nstemming, lemmatization, and numerous text vectorization options and\nalgorithms provided by the library.\nThe results show that the keyword-based classifier using word 2-grams\nworks as well as One-class Support Vector Machine with lemmatizing using the\nTerm Frequency\u2013Inverse Document Frequency preprocessing method in\nvulnerability detection. Vulnerability severities can be predicted better for\nCommon Vulnerability Scoring System version 2 than its version 3. The Linear\nSupport Vector Machine classifier got the highest F1-score in predicting both\nCommon Vulnerability Scoring System and Common Weakness Enumeration.\nThis thesis also presents a summary on the latest data available on the National\nVulnerability Database data feeds.", "language": "en", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Submitted by Paivi Vuorio (paelvuor@jyu.fi) on 2019-11-06T06:51:07Z\nNo. of bitstreams: 0", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Made available in DSpace on 2019-11-06T06:51:08Z (GMT). No. of bitstreams: 0\n Previous issue date: 2019", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.format.extent", "value": "62", "language": "", "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": "eng", "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": "common vulnerability scoring system", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "common weakness enumeration", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "Scikit-learn", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.title", "value": "Approaches and challenges of automatic vulnerability classification using natural language processing and machine learning techniques", "language": "", "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-201911064740", "language": "", "element": "identifier", "qualifier": "urn", "schema": "dc"}, {"key": "dc.type.ontasot", "value": "Pro gradu -tutkielma", "language": "fi", "element": "type", "qualifier": "ontasot", "schema": "dc"}, {"key": "dc.type.ontasot", "value": "Master\u2019s thesis", "language": "en", "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": "Tietojenk\u00e4sittelytiede", "language": "fi", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Computer Science", "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_bdcc", "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": "masterThesis", "language": null, "element": "type", "qualifier": "publication", "schema": "dc"}, {"key": "dc.subject.oppiainekoodi", "value": "601", "language": "", "element": "subject", "qualifier": "oppiainekoodi", "schema": "dc"}, {"key": "dc.subject.yso", "value": "koneoppiminen", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "luokitus (toiminta)", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "haavoittuvuus", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "datatiede", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "machine learning", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "classification", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "vulnerability", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "data science", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.format.content", "value": "fulltext", "language": null, "element": "format", "qualifier": "content", "schema": "dc"}, {"key": "dc.rights.url", "value": "https://rightsstatements.org/page/InC/1.0/", "language": null, "element": "rights", "qualifier": "url", "schema": "dc"}, {"key": "dc.type.okm", "value": "G2", "language": null, "element": "type", "qualifier": "okm", "schema": "dc"}]
|