Sustav za detekciju plagijata te određivanje autorstva izvornih kodova

master's thesis

• Title (english): System for Plagiarism Detection and Source Code Authorship Detection
• Author: Dino Rakipović
• Mentor: Ante Đerek (mentor)
• Committee member: Ante Đerek (predsjednik povjerenstva)
• Committee member: Zoran Kalafatić (član povjerenstva)
• Committee member: Klemo Vladimir (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2017-07-04, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Plagijati postaju sve veći problem u današnjem svijetu, zbog ogromnog rasta broja informacija na internetu vrlo se jednostavno može ukrasti tuđi rad te predstaviti ga kao svoj, tj. plagirati. U sklopu ovog diplomskog rada naglasak je bio na pronalasku plagijata među izvornim kodovima te smo tom problemu pristupili iz dva kuta, prvi je pronalazak sličnosti među parovima izvornih kodova korištenjem otisaka izvornih kodova dok je drugi
određivanje autora izvornog koda metodama strojnog učenja. Na kraju su ova dva pristupa spojena u web aplikaciju Turtle koja vrlo uspješno i u kratkom roku pronalazi plagijate među velikim brojem izvornih kodova(npr. laboratorijske vježbe ili programerska natjecanja).

Abstract (english)

Plagiarism is becoming bigger and bigger problem in today society, the reason behind it is that information available online is growing exponentially and it’s easy to steal from other authors and present it like your work. This thesis tackles the problem of detecting source code plagiarism from two different approaches, one is computing similarities between source code using source code fingerprints and other is deanonymizing authors of source code using machine learning. These approaches are then connected to a web application Turtle. This application can detect plagiarism between a large number of source code(e.g. laboratory assignments, programming competitions) rather well.

• Keywords: strojno učenje; plagijati; deanonimizacija; detekcija plagijata; izvorni kod
• Keywords (english): machine learning; plagiarism; deanonymization; plagiarism detection; source code
• Language: croatian
• URN:NBN: urn:nbn:hr:168:204239
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-03-14 00:20:57