Dataset Open Access
Constantinos Patsakis;
Fran Casino
{ "files": [ { "links": { "self": "https://zenodo.org/api/files/08c510cc-418b-4dc7-9bf0-6475a01478a4/dictionary_DGAs_dataset.zip" }, "checksum": "md5:92cd328d57a2ea5126eac1c1ef19a179", "bucket": "08c510cc-418b-4dc7-9bf0-6475a01478a4", "key": "dictionary_DGAs_dataset.zip", "type": "zip", "size": 52219491 } ], "owners": [ 116797 ], "doi": "10.5281/zenodo.4010620", "stats": { "version_unique_downloads": 11.0, "unique_views": 109.0, "views": 134.0, "version_views": 134.0, "unique_downloads": 11.0, "version_unique_views": 109.0, "volume": 574414401.0, "version_downloads": 11.0, "downloads": 11.0, "version_volume": 574414401.0 }, "links": { "doi": "https://doi.org/10.5281/zenodo.4010620", "conceptdoi": "https://doi.org/10.5281/zenodo.4010619", "bucket": "https://zenodo.org/api/files/08c510cc-418b-4dc7-9bf0-6475a01478a4", "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.4010619.svg", "html": "https://zenodo.org/record/4010620", "latest_html": "https://zenodo.org/record/4010620", "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.4010620.svg", "latest": "https://zenodo.org/api/records/4010620" }, "conceptdoi": "10.5281/zenodo.4010619", "created": "2020-09-01T13:36:18.438947+00:00", "updated": "2020-12-21T20:19:41.854210+00:00", "conceptrecid": "4010619", "revision": 6, "id": 4010620, "metadata": { "access_right_category": "success", "doi": "10.5281/zenodo.4010620", "version": "1.0", "license": { "id": "CC-BY-4.0" }, "title": "Exploiting Statistical and Structural Features for the Detection of Domain Generation Algorithms", "related_identifiers": [ { "scheme": "doi", "identifier": "10.5281/zenodo.4010619", "relation": "isVersionOf" } ], "relations": { "version": [ { "count": 1, "index": 0, "parent": { "pid_type": "recid", "pid_value": "4010619" }, "is_last": true, "last_child": { "pid_type": "recid", "pid_value": "4010620" } } ] }, "grants": [ { "code": "832735", "links": { "self": "https://zenodo.org/api/grants/10.13039/501100000780::832735" }, "title": "Lawful evidence collecting and continuity platform development", "acronym": "LOCARD", "program": "H2020", "funder": { "doi": "10.13039/501100000780", "acronyms": [], "name": "European Commission", "links": { "self": "https://zenodo.org/api/funders/10.13039/501100000780" } } }, { "code": "780498", "links": { "self": "https://zenodo.org/api/grants/10.13039/501100000780::780498" }, "title": "Cybersecurity Awareness and Knowledge Systemic High-level Application", "acronym": "YAKSHA", "program": "H2020", "funder": { "doi": "10.13039/501100000780", "acronyms": [], "name": "European Commission", "links": { "self": "https://zenodo.org/api/funders/10.13039/501100000780" } } }, { "code": "830929", "links": { "self": "https://zenodo.org/api/grants/10.13039/501100000780::830929" }, "title": "Cyber Security Network of Competence Centres for Europe", "acronym": "CyberSec4Europe", "program": "H2020", "funder": { "doi": "10.13039/501100000780", "acronyms": [], "name": "European Commission", "links": { "self": "https://zenodo.org/api/funders/10.13039/501100000780" } } } ], "keywords": [ "DGAs" ], "publication_date": "2020-09-01", "creators": [ { "orcid": "0000-0002-4460-9331", "affiliation": "University of Piraeus", "name": "Constantinos Patsakis" }, { "orcid": "0000-0003-4296-2876", "affiliation": "University of Piraeus", "name": "Fran Casino" } ], "access_right": "open", "resource_type": { "type": "dataset", "title": "Dataset" }, "description": "<p>This repository contains a dataset for the research of domain generation algorithms (DGAs) and machine learning. More precisely, it targets dictionary-based DGAs.</p>\n\n<p><em>Constantinos Patsakis, Fran Casino: "Exploiting Statistical and Structural Features for the Detection of Domain Generation Algorithms", Journal of Information Security and Applications, 2021.</em></p>\n\n<p>Features ordered as in the shared dataset:</p>\n\n<ul>\n\t<li>Family: DGA that the domain belongs to</li>\n\t<li>SLD: SLD of the Domain</li>\n\t<li>L-LEN: The length of Domain</li>\n\t<li>L-DIG: The number of digits in Domain</li>\n\t<li>L-CON-MAX: The maximum number of consecutive consonants Domain</li>\n\t<li>R-CON-VOW: Number of consonants divided by L-LEN </li>\n\t<li>L-SYM: The number of special characters</li>\n\t<li>R-SYM-LEN: L-SYM divided by L-LEN</li>\n\t<li>R-Dom-3G: Ratio of benign grams in Dom-3G</li>\n\t<li>R-Dom-4G: Ratio of benign grams in Dom-4G</li>\n\t<li>R-Dom-5G: Ratio of benign grams in Dom-5G</li>\n\t<li>L-W2: Number of words with more than 2 characters in Domain</li>\n\t<li>L-W3: Number of words with more than 3 characters in Domain</li>\n\t<li>R-WS-LEN: Dom-WS divided by L-LEN</li>\n\t<li>R-WDS-LEN: Dom-WDS divided by L-LEN</li>\n\t<li>R-W2-LEN: Dom-W2 divided by L-LEN</li>\n\t<li>R-W3-LEN: Dom-W3 divided by L-LEN</li>\n\t<li>M2-Dom-Ws: 2-Chain Markov English grams applied to Dom-WS</li>\n\t<li>M2-Dom-WDS: 2-Chain Markov English grams applied Dom-WDS</li>\n\t<li>E-Dom-WS: Entropy of Dom-WS </li>\n\t<li>E-Dom-WDS: Entropy of Dom-WDS</li>\n\t<li>E-Dom-W2: Entropy of Dom-W2</li>\n\t<li>E-Dom-W3: Entropy of Dom-W3</li>\n</ul>" } }
All versions | This version | |
---|---|---|
Views | 134 | 134 |
Downloads | 11 | 11 |
Data volume | 574.4 MB | 574.4 MB |
Unique views | 109 | 109 |
Unique downloads | 11 | 11 |