#LyX 2.3 created this file. For more info see http://www.lyx.org/ \lyxformat 544 \begin_document \begin_header \save_transient_properties true \origin unavailable \textclass scrbook \begin_preamble % enables calculations \usepackage{calc} % increases the bottom float placement fraction \renewcommand{\bottomfraction}{0.5} \end_preamble \options intoc,bibliography=totoc,index=totoc,BCOR10mm,captions=tableheading,titlepage \use_default_options true \master /usr/share/lyx/examples/thesis/thesis.lyx \maintain_unincluded_children false \language english \language_package default \inputencoding utf8 \fontencoding global \font_roman "lmodern" "default" \font_sans "lmss" "default" \font_typewriter "lmtt" "default" \font_math "auto" "auto" \font_default_family default \use_non_tex_fonts false \font_sc false \font_osf false \font_sf_scale 100 100 \font_tt_scale 100 100 \use_microtype false \use_dash_ligatures false \graphics default \default_output_format default \output_sync 0 \bibtex_command default \index_command default \float_placement h \paperfontsize 12 \spacing single \use_hyperref true \pdf_title "Abstract" \pdf_author "Your name" \pdf_bookmarks true \pdf_bookmarksnumbered true \pdf_bookmarksopen true \pdf_bookmarksopenlevel 2 \pdf_breaklinks false \pdf_pdfborder true \pdf_colorlinks false \pdf_backref false \pdf_pdfusetitle false \pdf_quoted_options "pdfpagelayout=OneColumn, pdfnewwindow=true, pdfstartview=XYZ, plainpages=false" \papersize a4paper \use_geometry false \use_package amsmath 2 \use_package amssymb 2 \use_package cancel 1 \use_package esint 1 \use_package mathdots 1 \use_package mathtools 1 \use_package mhchem 1 \use_package stackrel 1 \use_package stmaryrd 1 \use_package undertilde 1 \cite_engine basic \cite_engine_type default \biblio_style plain \use_bibtopic false \use_indices false \paperorientation portrait \suppress_date false \justification true \use_refstyle 0 \use_minted 0 \index Index \shortcut idx \color #008000 \end_index \secnumdepth 3 \tocdepth 3 \paragraph_separation skip \defskip medskip \is_math_indent 1 \math_indentation default \math_numbering_side default \quotes_style english \dynamic_quotes 0 \papercolumns 1 \papersides 2 \paperpagestyle plain \tracking_changes false \output_changes false \html_math_output 0 \html_css_as_file 0 \html_be_strict false \end_header \begin_body \begin_layout Chapter* Povzetek \end_layout \begin_layout Standard \begin_inset ERT status open \begin_layout Plain Layout \backslash addcontentsline{toc}{chapter}{Povzetek in ključne besede} \end_layout \end_inset \begin_inset Note Note status open \begin_layout Plain Layout adds table of contents entry \end_layout \end_inset \end_layout \begin_layout Standard Porazdeljene razpršilne tabele (angl. distributed hash table) so razpršilne tabele, ki podatke, ponavadi so to dokumenti, strukturirani kot vrednost in njen pripadajoč ključ, hranijo distribuirano na več vozliščih, kjer se podatki shranjujejo. V računalniških sistemih se DHT uporablja za hrambo podatkov v omrežjih P2P (angl. peer to peer), kjer se podatki vseh uporabnikov enakomerno porazdelijo med vozlišča in so tako decentralizirani in preprosto dostopni članom omrežja. Ker se podatki izmenjujejo znotraj omrežja na vozliščih, ki z izvorom in destinacijo podatkov niso povezani, jih lahko vozlišča v velikih količinah shranjujejo. \end_layout \begin_layout Standard V raziskovalni nalogi je preverjena praktična zmožnost pridobivanja velike količine podatkov v omrežju BitTorrent za P2P izmenjavo datotek, pridobljeni podatki pa so analizirani. Vsaka poizvedba po seznamu imetnikov datotek vsebuje ključ podatka v DHT in se prenese preko okoli \begin_inset Formula $\log_{2}n$ \end_inset vozlišč, kjer je \begin_inset Formula $n$ \end_inset število vseh uporabnikov v omrežju. Ker vsaka poizvedba obišče tako veliko število vozlišč, lahko eno vozlišče prejme veliko obstoječih ključev v omrežju, s katerimi si lahko prenese metapodatke v omrežju BitTorrent. \end_layout \begin_layout Standard Naloga se osredotoči na pridobivanje metapodatkov v omrežju BitTorrent, glede prenosa datotek, ki jih ponujajo računalniki, pa se vsled njihove velikosti ne opredeli. Metapodatki konceptualno sicer niso shranjeni v DHT (namesto metapodatkov o datotekah so v omrežju shranjeni seznami računalnikov, od katerih si metapodatke lahko prenesemo), vendar odkrivanje njihovega obstoja omogoči DHT. \end_layout \begin_layout Paragraph* Ključne besede \end_layout \begin_layout Standard porazdeljena razpršilna tabela, distribuirani sistemi, P2P omrežje, podatkovno rudarjenje, BitTorrent \end_layout \begin_layout Chapter* Summary \end_layout \begin_layout Paragraph Title \end_layout \begin_layout Standard Harvesting data from a DHT network \end_layout \begin_layout Paragraph Subtitle \end_layout \begin_layout Standard Analysis of a data stream going through BitTorrent nodes and metadata downloadin g \end_layout \begin_layout Standard \begin_inset ERT status open \begin_layout Plain Layout \backslash addcontentsline{toc}{chapter}{Summary and keywords} \end_layout \end_inset \begin_inset Note Note status open \begin_layout Plain Layout adds table of contents entry \end_layout \end_inset \end_layout \begin_layout Standard Distributed hash tables are hash tables that store data, usually documents, structured by key-value association, distributed amongst many nodes, where they are kept for longer periods of time. In computer networks are DHTs used for data storage in peer-to-peer networks, where common data are evenly distributed amongst nodes. Consequentially are those data stored in a decentralized manner and are accessible to every node in the network with low complexity. Because the data are exchanged across nodes that are neither source or destination of a datum, they can obtain new data and store them in large quantities. \end_layout \begin_layout Standard A practical possibility of harvesting large amounts of data in BitTorrent network for peer-to-peer file transfer is presented and harvested data are analyzed. Every query for file providers contains the key for the queried-for list and traverses over around \begin_inset Formula $\log_{2}n$ \end_inset nodes, where \begin_inset Formula $n$ \end_inset means the number of participants in the network. Because every query visits such a large amount of nodes, can every node receive a large amount of existing keys in the DHT that can be used for downloading metadata of BitTorrent files. \end_layout \begin_layout Standard This research paper focuses solely on harvesting metadata, not on downloading shared files, primarily due to their extreme size. Metadata conceptually aren't stored in the DHT (instead of file metadata, lists of computer addresses, from which metadata can be downloaded, are stored), but the DHT enables their discovery. \end_layout \begin_layout Paragraph Keywords \end_layout \begin_layout Standard distributed hash table, distributed systems, peer-to-peer network, data mining, BitTorrent \end_layout \end_body \end_document