{"id":35574,"date":"2025-02-27T04:37:04","date_gmt":"2025-02-27T03:37:04","guid":{"rendered":"https:\/\/kinit.sk\/aiming-to-catchem-all-data-for-network-intrusion-detection\/"},"modified":"2025-04-15T14:19:51","modified_gmt":"2025-04-15T12:19:51","slug":"chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach","status":"publish","type":"post","link":"https:\/\/kinit.sk\/sk\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\/","title":{"rendered":"Chy\u0165me ich v\u0161etky: N\u00e1\u0161 v\u00fdskum v oblasti d\u00e1t pre detekciu \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach"},"content":{"rendered":"
\n

V dne\u0161nom svete je internetov\u00e9 pripojenie pova\u017eovan\u00e9 za nutnos\u0165 pre v\u00e4\u010d\u0161inu \u013eud\u00ed. Internet zohr\u00e1va k\u013e\u00fa\u010dov\u00fa \u00falohu pri fungovan\u00ed firiem, online komunik\u00e1cii, vzdel\u00e1van\u00ed, ale aj vo\u013eno\u010dasov\u00fdch aktivit\u00e1ch. Odhaduje sa, \u017ee v roku 2024 pou\u017e\u00edvalo internet pribli\u017ene 5,5 miliardy \u013eud\u00ed (68 % svetovej popul\u00e1cie) (Petrosyan, 2024). Zamysleli ste sa v\u0161ak niekedy nad situ\u00e1ciou, ke\u010f by Internet nefungoval? U\u017e chv\u00ed\u013ekov\u00fd v\u00fdpadok by bezpochyby sp\u00f4sob irit\u00e1ciu mnoh\u00fdch \u013eud\u00ed, nieko\u013ekohodinov\u00e9 v\u00fdpadky v\u0161ak vedia sp\u00f4sobi\u0165 miliardov\u00e9 \u0161kody a dokonca aj ohrozenie \u013eudsk\u00fdch \u017eivotov. Zoh\u013ead\u0148ovanie aspektov kyberbezpe\u010dnosti je preto v modern\u00fdch syst\u00e9moch nevyhnutn\u00e9.<\/strong><\/p>\n<\/div>\n\n

\n

Kybernetick\u00e1 bezpe\u010dnos\u0165 sa vo v\u0161eobecnosti del\u00ed na tri hlavn\u00e9 odvetvia: prevencia, detekcia a reakcia. Prevencia zah\u0155\u0148a techniky na obmedzenie mo\u017enost\u00ed \u00fatoku, v\u00fdsledkom \u010doho je zna\u010dn\u00e9 s\u0165a\u017eenie alebo kompletn\u00e9 zamedzenie jeho prevedenia. Pr\u00edklady t\u00fdchto techn\u00edk zah\u0155\u0148aj\u00fa in\u0161tal\u00e1ciu softv\u00e9rov\u00fdch aktualiz\u00e1ci\u00ed, korektn\u00fa konfigur\u00e1ciu syst\u00e9mov, alebo pou\u017e\u00edvanie \u0161pecializovan\u00fdch bezpe\u010dnostn\u00fdch mechanizmov, ako napr\u00edklad firewally. Dokonal\u00e1 prevencia je v\u0161ak vzh\u013eadom na mno\u017estvo faktorov (napr. zlo\u017eitos\u0165 syst\u00e9mov a \u013eudsk\u00e9 chyby) nedosiahnute\u013en\u00e1 (Apruzzese a kol., 2023). Z tohto d\u00f4vodu je potrebn\u00e9 kl\u00e1s\u0165 zna\u010dn\u00fd d\u00f4raz aj na opatrenia na detekciu kybernetick\u00fdch \u00fatokov a n\u00e1sledn\u00fa reakciu.<\/p>\n<\/div>\n\n

\n

\u00datoky je obecne mo\u017en\u00e9 detegova\u0165 na dvoch \u00farovniach: na koncov\u00fdch syst\u00e9moch (ang. host-based) a na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach (ang. network-based). V KInIT-e sa zameriavame na obe z nich. Koncov\u00fdm syst\u00e9mom sa venuje Martin Mocko v jeho pr\u00e1ci zameranej na zhlukovanie malv\u00e9ru<\/a>, zatia\u013e \u010do Patrik Goldschmidt pracuje na d\u00e1tovo-centrickom poh\u013eade na dom\u00e9nu detekcie \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach. Tento blog stru\u010dne predstav\u00ed oblas\u0165 detekcie \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach (ang. network intrusion detection, skratka NID) a prezentuje zistenia n\u00e1\u0161ho ned\u00e1vneho \u010dl\u00e1nku o NID d\u00e1tov\u00fdch sad\u00e1ch.<\/p>\n<\/div>\n\n

\n
\"\"<\/figure>\n<\/div><\/div>\n\n
\n

Obr\u00e1zok 1: Tri oblasti kybernetickej bezpe\u010dnosti: Prevencia (zelen\u00fdm), detekcia (\u017elt\u00fdm) a reakcia (oran\u017eov\u00fdm). N\u00e1\u0161 v\u00fdskum v KInIT sa zameriava predov\u0161etk\u00fdm na oblas\u0165 detekcie, ktor\u00fa mo\u017eno \u010falej rozdeli\u0165 na detekciu zalo\u017een\u00fa na koncov\u00fdch staniciach (malv\u00e9r) a na detekciu na sieti so snahou odhali\u0165 \u0161kodliv\u00e9 aktivity v prostredn\u00edctvom anal\u00fdzy sie\u0165ovej prev\u00e1dzky.<\/em><\/em><\/p>\n<\/div>\n\n

\n

Detekcia \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach<\/h2>\n<\/div>\n\n
\n

Ako sme spom\u00ednali, detekcia \u00fatokov m\u00f4\u017ee by\u0165 prev\u00e1dzan\u00e1 na \u00farovni samotn\u00fdch koncov\u00fdch stan\u00edc alebo po\u010d\u00edta\u010dovej siete. Detekciu v po\u010d\u00edta\u010dov\u00fdch sie\u0165ach vykon\u00e1vaj\u00fa syst\u00e9my na detekciu naru\u0161enia siete (ang. network intrusion detection system \u2013 NIDS), teda hardv\u00e9rov\u00e9 zariadenia alebo softv\u00e9rov\u00ed agenti monitoruj\u00faci po\u010d\u00edta\u010dov\u00fa sie\u0165 a identifikuj\u00fa jej potenci\u00e1lne neopr\u00e1vnen\u00e9 pou\u017eitie, nespr\u00e1vne pou\u017eitie, alebo zneu\u017eitie. V z\u00e1vislosti od sp\u00f4sobu detekcie \u00fatoku rozli\u0161ujeme syst\u00e9my zalo\u017een\u00e9 na signat\u00farach (reaguj\u00fa na zn\u00e1me vzory \u00fatokov) a syst\u00e9my zalo\u017een\u00e9 na anom\u00e1li\u00e1ch (reaguj\u00fa na nezn\u00e1me odch\u00fdlky od norm\u00e1lneho stavu). Hoci na tieto \u00fa\u010dely m\u00f4\u017eeme pou\u017ei\u0165 mno\u017estvo pr\u00edstupov, met\u00f3dy strojov\u00e9ho u\u010denia a umelej inteligencie sa v mnoh\u00fdch aspektoch uk\u00e1zali ako \u00fa\u010dinn\u00e9 a dostali sa do popredia v novodobom NIDS v\u00fdskume.<\/p>\n<\/div>\n\n

\n

Bez oh\u013eadu na algoritmus alebo met\u00f3du detekcie, detek\u010dn\u00e9 syst\u00e9my sa sna\u017eia maximalizova\u0165 mieru detekcie \u00fatokov (ide\u00e1lne ich odhali\u0165 100%) a z\u00e1rove\u0148 minimalizova\u0165 mieru falo\u0161n\u00fdch poplachov, t.j., legit\u00edmnu komunik\u00e1ciu ozna\u010den\u00fa ako \u0161kodliv\u00fa (ide\u00e1lne 0%). Za t\u00fdmto \u00fa\u010delom ako v\u00fdskumn\u00edci potrebujeme r\u00f4zne referen\u010dn\u00e9 d\u00e1tov\u00e9 sady, ktor\u00e9 sl\u00fa\u017eia na vyhodnotenie navrhovan\u00fdch met\u00f3d na pos\u00fadenie ich u\u017eito\u010dnosti pri nasaden\u00ed v skuto\u010dn\u00fdch sie\u0165ach. Aspekt d\u00e1t je v\u0161ak ve\u013emi problematick\u00fd vzh\u013eadom na r\u00f4zne \u0161pecifick\u00e9 charakteristiky NIDS dom\u00e9ny.<\/p>\n<\/div>\n\n

\n
\"\"<\/figure>\n<\/div><\/div>\n\n
\n

Obr\u00e1zok 2: Umiestnenie syst\u00e9mu detekcie naru\u0161enia siete (NIDS) v po\u010d\u00edta\u010dovej sieti. Ako je zn\u00e1zornen\u00e9, NIDS s\u00fa zvy\u010dajne umiestnen\u00e9 priamo pred internetovou br\u00e1nou, pred ktorou sa m\u00f4\u017ee nach\u00e1dza\u0165 aj firewall. NIDS monitoruje aktivitu siete kontrolou jej prev\u00e1dzky a v pr\u00edpade zistenia podozrivej aktivity vyvol\u00e1va v\u00fdstrahu, alebo blokuje komunik\u00e1ciu priamo.<\/em><\/em><\/p>\n<\/div>\n\n

\n

Vlastnosti \u0161pecifick\u00e9 pre NIDS dom\u00e9nu a ich vplyv na d\u00e1ta<\/h2>\n<\/div>\n\n
\n

Na rozdiel od typick\u00fdch aplika\u010dn\u00fdch oblast\u00ed strojov\u00e9ho u\u010denia (ML), ako je spracovanie obrazu alebo re\u010di sa mus\u00ed dom\u00e9na detekcie \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach navy\u0161e pot\u00fdka\u0165 so \u0161pecifick\u00fdmi vlastnos\u0165ami, ktor\u00e9 zna\u010dne obmedzuj\u00fa aplik\u00e1cie met\u00f3d zalo\u017een\u00fdch na d\u00e1tach, ako je pr\u00e1ve strojov\u00e9 u\u010denie. Jednou z tak\u00fdchto v\u00fdznamn\u00fdch vlastnost\u00ed je vysok\u00e1 variabilita. Ke\u010f\u017ee je ka\u017ed\u00e1 po\u010d\u00edta\u010dov\u00e1 sie\u0165 jedine\u010dn\u00e1, vzory ich aktiv\u00edt sa medzi nimi do zna\u010dnej miery l\u00ed\u0161ia. Ako d\u00f4sledok tohto faktu je, \u017ee detek\u010dn\u00fd model tr\u00e9novan\u00fd na jednej sieti bude pri pou\u017eit\u00ed na druhej sieti pravdepodobne dosahova\u0165 neuspokojiv\u00e9 v\u00fdsledky. Okrem toho, variabilita medzi sie\u0165ami nie je v\u0161etko. Variabilita sa dokonca vz\u0165ahuje aj na prev\u00e1dzku v r\u00e1mci jednej siete, ke\u010f\u017ee sa existuj\u00face vzory prev\u00e1dzky m\u00f4\u017eu na rovnakej sieti v priebehu \u010dasu z\u00e1sadne meni\u0165. T\u00e1to zmena, odborne zn\u00e1ma ako konceptu\u00e1lny alebo modelov\u00fd posun (ang. concept\/model drift) sp\u00f4sobuje zhor\u0161enie v\u00fdkonu, ak sa natr\u00e9novan\u00fd model pravidelne neaktualizuje.<\/p>\n<\/div>\n\n

\n

Ke\u010f\u017ee sa syst\u00e9my NIDS zameriavaj\u00fa na odha\u013eovanie \u0161kodliv\u00e9ho spr\u00e1vania, \u00fato\u010dn\u00edci sa ich prirodzene pok\u00fa\u0161aj\u00fa ob\u00eds\u0165. T\u00e1to vlastnos\u0165 nepriate\u013esk\u00e9ho prostredia \u010falej zni\u017euje detek\u010dn\u00e9 schopnosti modelu, ke\u010f\u017ee sa \u00fato\u010dn\u00edci sna\u017eia met\u00f3du explicitne ob\u00eds\u0165. Medzi \u010fal\u0161ie nepr\u00edjemn\u00e9 vlastnosti dom\u00e9ny patria probl\u00e9my s re\u00e1lnou prev\u00e1dzkou, ke\u010f\u017ee jej zachytenie m\u00f4\u017ee ohrozi\u0165 s\u00fakromie pou\u017e\u00edvate\u013eov. Jej zna\u010dkovanie navy\u0161e nie je mo\u017en\u00e9 vykon\u00e1va\u0165 s absol\u00fatnou istotou. V d\u00f4sledku spom\u00ednan\u00fdch vlastnost\u00ed s\u00fa d\u00e1ta pre NID \u00fa\u010dely \u010dasto simulovan\u00e9, \u010do vedie k r\u00f4znym probl\u00e9m s realistickos\u0165ou, ke\u010f\u017ee simulovan\u00e9 \u00fadaje nemusia spr\u00e1vne reprezentova\u0165 d\u00e1ta z re\u00e1lneho sveta.<\/p>\n<\/div>\n\n

\n

Vy\u0161\u0161ie uveden\u00e9 vlastnosti dom\u00e9ny z\u00e1sadne ovplyv\u0148uj\u00fa d\u00e1ta sie\u0165ovej prev\u00e1dzky a ich kvalitu. V d\u00f4sledku tohto obsahuj\u00fa existuj\u00face d\u00e1tov\u00e9 sady viacer\u00e9 obmedzenia, ktor\u00e9 limituj\u00fa ich pou\u017eite\u013enos\u0165, ako aj d\u00f4veryhodnos\u0165 v\u00fdsledkov z\u00edskan\u00fdch pri ich pou\u017eit\u00ed. V r\u00e1mci n\u00e1\u0161ho v\u00fdskumu sme identifikovali dev\u00e4\u0165 typick\u00fdch obmedzen\u00ed d\u00e1tov\u00fdch s\u00e1d a rozdelili ich pod\u013ea sp\u00f4sobu vzniku: sp\u00f4soben\u00e9 \u010dlovekom, sp\u00f4soben\u00e9 dom\u00e9nou a ich kombin\u00e1cia. Zatia\u013e \u010do obmedzenia sp\u00f4soben\u00e9 \u010dlovekom je mo\u017en\u00e9 spr\u00e1vnou manipul\u00e1ciou s d\u00e1tami \u00faplne odstr\u00e1ni\u0165, obmedzenia kv\u00f4li dom\u00e9ne s\u00fa sp\u00f4soben\u00e9 jej prirodzen\u00fdmi vlastnos\u0165ami, a preto je ich rie\u0161enie problematickej\u0161ie. Obmedzenia zh\u0155\u0148ame v obr\u00e1zku 3.<\/p>\n<\/div>\n\n

\n
\"\"<\/figure>\n<\/div><\/div>\n\n
\n

Obr\u00e1zok 3: Typick\u00e9 obmedzenia d\u00e1tov\u00fdch s\u00e1d pre detekciu \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach. Ako je zn\u00e1zornen\u00e9, niektor\u00e9 s\u00fa priamym d\u00f4sledkom vlastnost\u00ed \u0161pecifick\u00fdch pre dan\u00fa dom\u00e9nu a je n\u00e1ro\u010dn\u00e9 ich rie\u0161i\u0165 (napr. aktu\u00e1lnos\u0165), niektor\u00e9 s\u00fa sp\u00f4soben\u00e9 predov\u0161etk\u00fdm \u013eudsk\u00fdm faktorom a mo\u017eno ich \u00faplne odstr\u00e1ni\u0165 (napr. dokument\u00e1cia) a tie, ktor\u00e9 le\u017eia v priese\u010dn\u00edku oboch je mo\u017en\u00e9 adresova\u0165 iba \u010diasto\u010dne (napr. nevyv\u00e1\u017eenos\u0165 tried – prev\u00e1dzka NID je prirodzene nevyv\u00e1\u017een\u00e1, ale autori d\u00e1tov\u00fdch s\u00e1d sa ju m\u00f4\u017eu pok\u00fasi\u0165 zn\u00ed\u017ei\u0165)<\/em><\/em><\/p>\n<\/div>\n\n

\n

V s\u00fa\u010dasnosti je jedn\u00fdm z najv\u00fdraznej\u0161\u00edch probl\u00e9mov d\u00e1tov\u00fdch s\u00e1d ich aktu\u00e1lnos\u0165, ktor\u00e1 je d\u00f4sledkom vplyvu v\u00fdrazn\u00e9ho konceptu\u00e1lneho posunu v dom\u00e9ne. Ke\u010f\u017ee d\u00e1tov\u00e9 sady zachyt\u00e1vaj\u00fa ur\u010dit\u00fd bod v \u010dase v minulosti, ich vzory prev\u00e1dzky maj\u00fa tendenciu zastar\u00e1va\u0165 relat\u00edvne r\u00fdchlo, \u010d\u00edm sa hodnota zozbieran\u00fdch d\u00e1t zni\u017euje. Zber d\u00e1t z re\u00e1lnych siet\u00ed navy\u0161e prid\u00e1va \u010fal\u0161ie probl\u00e9my ako neistota pri zna\u010dkovan\u00ed prev\u00e1dzky a obavy o s\u00fakromie u\u017e\u00edvate\u013eov, v\u00fdsledkom \u010doho autori d\u00e1tov\u00fdch s\u00e1d preferuj\u00fa simulova\u0165 d\u00e1ta prostredn\u00edctvom testovac\u00edch prostred\u00ed a tvori\u0165 syntetick\u00fa prev\u00e1dzku, zni\u017euj\u00fac realizmus d\u00e1t. Z tohto d\u00f4vodu sa nedostato\u010dn\u00fd realizmus referen\u010dn\u00fdch d\u00e1tov\u00fdch s\u00e1d pova\u017euje za jednu z hlavn\u00fdch prek\u00e1\u017eok pri nasadzovan\u00ed NIDS zalo\u017een\u00fdch na detekci\u00ed anom\u00e1li\u00ed do re\u00e1lnych produk\u010dn\u00fdch prostred\u00ed (Sommer a Paxson, 2010).<\/p>\n<\/div>\n\n

\n

N\u00e1\u0161 v\u00fdskum v oblasti d\u00e1t pre detekciu \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach<\/h2>\n<\/div>\n\n
\n

Napriek tomu, \u017ee bolo ned\u00e1vno zverejnen\u00fdch mno\u017estvo d\u00e1tov\u00fdch s\u00e1d pre NID \u00fa\u010dely, v\u00fdskumn\u00edci \u010dasto nepoznaj\u00fa ich vhodn\u00e9 pr\u00edpady pou\u017eitia v d\u00f4sledku ich nedostato\u010dn\u00e9ho presk\u00famania. Tento fakt sa stal motiv\u00e1ciou pre n\u00e1\u0161 ned\u00e1vny \u010dl\u00e1nok<\/a> (Goldschmidt a Chud\u00e1, 2025), ktor\u00fd je v s\u00fa\u010dasnosti v recenznom konan\u00ed v prest\u00ed\u017enom vedeckom \u010dasopise computers & Security. V tomto \u010dl\u00e1nku zdru\u017eujeme poznatky o existuj\u00facich d\u00e1tov\u00fdch limit\u00e1ci\u00e1ch, na\u010drt\u00e1vame ich prepojenie k spom\u00ednan\u00fdm dom\u00e9novo-\u0161pecifick\u00fdm vlastnostiam, a poskytujeme preh\u013ead verejn\u00fdch referen\u010dn\u00fdch d\u00e1tov\u00fdch s\u00e1d pre \u00fa\u010dely detekcie \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach. Okrem toho \u010dl\u00e1nok diskutuje aj odpor\u00fa\u010dania na spr\u00e1vny v\u00fdber, pou\u017eitie, a tvorbu NID d\u00e1t.<\/p>\n<\/div>\n\n

\n

V na\u0161om \u010dl\u00e1nku sme presk\u00famali 89 popul\u00e1rnych NID d\u00e1tov\u00fdch s\u00e1d a extrahovali 13 vlastnost\u00ed, ktor\u00e9 s\u00fali\u017eili na ich porovnanie. Extrakciu sme vykonali prostredn\u00edctvom manu\u00e1lneho stiahnutia a explorat\u00edvnej d\u00e1tovej anal\u00fdzy (EDA). V \u010dl\u00e1nku diskutujeme vlastnosti ako objem d\u00e1t, d\u013a\u017eka z\u00e1chytu, typy vykonan\u00fdch \u00fatokov, typ prostredia, alebo ve\u013ekos\u0165 po\u010d\u00edta\u010dovej siete pou\u017eitej pre z\u00e1chyt. Za t\u00fdmto \u00fa\u010delom zav\u00e1dzame aj nov\u00fa taxon\u00f3miu kybernetick\u00fdch \u00fatokov, ako aj taxon\u00f3miu pre d\u00e1tov\u00e9 sady. D\u00fafame, \u017ee v\u010faka t\u00fdmto inform\u00e1ci\u00e1m u\u013eah\u010d\u00edme bud\u00faci v\u00fdskum a v\u00fdvoj v NID oblasti s cie\u013eom dosiahnu\u0165 lep\u0161iu replikovate\u013enos\u0165, realistickos\u0165 a robustnos\u0165 navrhovan\u00fdch NIDS met\u00f3d.<\/p>\n<\/div>\n\n

\n

V \u010dl\u00e1nku \u010falej predstavujeme nieko\u013eko zauj\u00edmav\u00fdch zisten\u00ed na z\u00e1klade anal\u00fdzy trendov sk\u00faman\u00fdch d\u00e1tov\u00fdch s\u00e1d. Spozorovali sme, \u017ee tradi\u010dn\u00e9 d\u00e1tov\u00e9 sady KDD ’99 and NSL-KDD pou\u017e\u00edvan\u00e9 v dom\u00e9ne posledn\u00fdch 25 rokov u\u017e nepatria medzi najpopul\u00e1rnej\u0161ie d\u00e1tov\u00e9 sady v teraj\u0161om v\u00fdskume. Tento trend ukazuje, \u017ee komunita si uvedomuje nevhodnos\u0165 t\u00fdchto d\u00e1tov\u00fdch s\u00e1d, a pre\u0161la na in\u00e9, nov\u0161ie d\u00e1tov\u00e9 sady ako napr\u00edklad CIC-IDS2017. \u010eal\u0161ie zistenia ukazuj\u00fa rozmach pulik\u00e1ci\u00ed v oblasti d\u00e1t, ke\u010f\u017ee 51 z 89 sk\u00faman\u00fdch s\u00e1d bolo zozbieran\u00fdch od roku 2020, ako zn\u00e1zor\u0148ujeme na obr\u00e1zku 4. Okrem toho, viac ako tri \u0161tvrtiny t\u00fdchto d\u00e1tov\u00fdch s\u00e1d je \u0161pecializovan\u00fdch – teda explicitne zameran\u00fdch na konkr\u00e9tny typ \u00fatokov alebo sie\u0165ov\u00e9 prostredie pre simul\u00e1ciu.<\/p>\n<\/div>\n\n

\n
\"\"<\/figure>\n<\/div><\/div>\n\n
\n

Obr\u00e1zok 4: Po\u010det NID d\u00e1tov\u00fdch s\u00e1d pod\u013ea roku uverejnenia. Ako zn\u00e1zor\u0148ujeme na obr\u00e1zku, po\u010det publikovan\u00fdch s\u00e1d v posledn\u00fdch rokoch r\u00e1stol polynomicky.<\/em><\/em><\/p>\n<\/div>\n\n

\n

Anal\u00fdza be\u017enej (ne\u0161kodnej) sie\u0165ovej prev\u00e1dzky uk\u00e1zala \u0161tyri hlavn\u00e9 mo\u017enosti jej generovania \u2013 emul\u00e1cia na b\u00e1ze profilov, emul\u00e1cia s pou\u017eit\u00edm gener\u00e1torov prev\u00e1dzky, zapojenie \u013eud\u00ed do procesu, a \u00fapln\u00e9 vyl\u00fa\u010denie norm\u00e1lnej prev\u00e1dzky. Napriek spomenut\u00fdm mo\u017enostiam v\u0161ak ost\u00e1va dosiahnutie ealizmu be\u017enej prev\u00e1dzky v\u00fdznamnou a n\u00e1ro\u010dnou v\u00fdskumnou ot\u00e1zkou. Na druhej strane, generovanie \u0161kodlivej prev\u00e1dzky je o nie\u010do jednoduch\u0161ie, ke\u010f\u017ee autori d\u00e1tov\u00fdch s\u00e1d m\u00f4\u017eu pou\u017ei\u0165 rovnak\u00e9 n\u00e1stroje ako re\u00e1lni \u00fato\u010dn\u00edci. Aj ke\u010f je v s\u00fa\u010dasnosti generovanie syntetick\u00fdch d\u00e1t v NID dom\u00e9ne zriedkav\u00e9, ver\u00edme, \u017ee m\u00e1 ve\u013ek\u00fd potenci\u00e1l na vyrie\u0161enie nieko\u013eko d\u00e1tov\u00fdch probl\u00e9mov a limit\u00e1ci\u00ed v bud\u00facnosti.<\/p>\n<\/div>\n\n

\n

\u010co \u010falej s v\u00fdskumom d\u00e1t pre detekciu \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach \u010falej?<\/h2>\n<\/div>\n\n
\n

Behom n\u00e1\u0161ho sk\u00famania d\u00e1tov\u00fdch s\u00e1d sme takisto identifikovali nieko\u013eko s\u013eubn\u00fdch smerov pre bud\u00faci v\u00fdskum a v\u00fdvoj v NID dom\u00e9ne. Vo v\u0161eobecnosti a bude bud\u00faci v\u00fdskum s\u00fastredi\u0165 okolo jednej hlavnej v\u00fdskumnej ot\u00e1zky: \u201cAko u\u013eah\u010di\u0165 pr\u00edstup k spr\u00e1vnym, relevantn\u00fdm a realistick\u00fdm d\u00e1tam, ktor\u00e9 reflektuj\u00fa s\u00fa\u010dasn\u00fd kyberbezpe\u010dnostn\u00fd priestor a sie\u0165ov\u00e9 charakteristiky?<\/em>\u201d <\/em>Na z\u00e1klade tejto ot\u00e1zky sme bud\u00faci v\u00fdskum rozdelli do \u0161tyroch hlavn\u00fdch oblast\u00ed \u2013 1) generovanie d\u00e1t, zameran\u00e9 na z\u00edskanie aktu\u00e1lnych a realistick\u00fdch d\u00e1t; 2) spracovanie d\u00e1t, sk\u00famaj\u00face typy a granularitu \u010d\u0155t najvhodnej\u0161ie na detekciu ur\u010dit\u00fdch typov \u00fatokov; 3) valid\u00e1cia d\u00e1t, formalizuj\u00faca metriky a met\u00f3dy na verifik\u00e1ciu d\u00e1t a ich kvality; a 4) publik\u00e1cia d\u00e1t, sk\u00famaj\u00faca ako distribuova\u0165 \u00fadaje k ich u\u017e\u00edvate\u013eom r\u00fdchlej\u0161ie s kvalitnej\u0161ou dokument\u00e1ciou.<\/p>\n<\/div>\n\n

\n
\"\"<\/figure>\n<\/div><\/div>\n\n
\n

Obr\u00e1zok 5: Bud\u00face smery v\u00fdskumu a v\u00fdvoja NID d\u00e1t. Del\u00edme ich na oblasti zameran\u00e9 na generovanie, spracovanie, valid\u00e1ciu a publikovanie d\u00e1t.<\/em><\/em><\/p>\n<\/div>\n\n

\n

Jedn\u00fdm z najd\u00f4le\u017eitej\u0161\u00edch v\u00fdskumno-v\u00fdvojov\u00fdch smerov v oblasti NID d\u00e1t je rie\u0161enie problematiky aktu\u00e1lnosti d\u00e1t, ako aj r\u00fdchlej\u0161ia distrib\u00facia realistick\u00fdch d\u00e1t k ich koncov\u00fdm u\u017e\u00edvate\u013eom. V na\u0161om \u010dl\u00e1nku ako rie\u0161enie navrhujeme princ\u00edp kontinu\u00e1lneho zberu d\u00e1t z re\u00e1lnych po\u010d\u00edta\u010dov\u00fdch siet\u00ed a ich n\u00e1sledn\u00e9 automatick\u00e9 zna\u010denie a publikovanie. Podobn\u00e9 projekty, ako MAWILab alebo Kyoto 2006+, boli navrhnut\u00e9 u\u017e v minulosti, ale v s\u00fa\u010dasnosti n\u00e1m nie je zn\u00e1my \u017eiadny podobn\u00fd akt\u00edvny projekt. Z tohto d\u00f4vodu s\u00fa tak\u00e9to projekty ve\u013emi \u017eiaduce, ke\u010f\u017ee umo\u017en\u00ed v\u00fdskumn\u00edkom a odborn\u00edkom z praxe pr\u00edstup k najnov\u0161\u00edm vzorom prev\u00e1dzky na overovanie ich navrhovan\u00fdch syst\u00e9mov. Kontinu\u00e1lny zber d\u00e1t si v\u0161ak vy\u017eaduje pokroky v \u010fal\u0161\u00edch aspektoch, ako napr\u00edklad presn\u00e9 zna\u010dkovanie re\u00e1lnych d\u00e1t, ktor\u00e9 je nevyhnut\u00e9 pre fin\u00e1lnu kvalitu \u00fadajov.<\/p>\n<\/div>\n\n

\n

Tak \u010di onak, detekcia \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach je typick\u00fdm pr\u00edkladom klasickej kyberbezpe\u010dnostnej situ\u00e1cie \u2013 hry na ma\u010dku a my\u0161. V tejto hre dobr\u00ed ochrancovia siete st\u00e1le nah\u00e1\u0148aj\u00fa zl\u00fdch \u00fato\u010dn\u00edkov, ktor\u00ed s\u00fa v\u0161ak st\u00e1le schopn\u00ed pr\u00eds\u0165 s nov\u00fdmi a viac sofistikovanej\u0161\u00edmi \u00fatokmi. Napriek tomu v\u0161ak ver\u00edme, \u017ee neust\u00e1ly v\u00fdskum v NIDS oblasti a \u010fal\u0161\u00edch bezpe\u010dnostn\u00fdch techn\u00edk poskytne dostato\u010dn\u00fa bezpe\u010dnos\u0165 pre v\u00e4\u010d\u0161inu internetov\u00fdch pou\u017e\u00edvate\u013eov.<\/p>\n<\/div>\n\n

\n

Z\u00e1ver<\/h2>\n<\/div>\n\n
\n

D\u00e1ta s\u00fa srdcom a du\u0161ou ka\u017ed\u00e9ho syst\u00e9mu strojov\u00e9ho u\u010denia. Ke\u010f\u017ee v\u00e4\u010d\u0161ina NIDS v\u00fdskumu v s\u00fa\u010dasnosti strojov\u00e9 u\u010denie pou\u017e\u00edva, snaha o zabezpe\u010denie vysokej kvality d\u00e1t je k\u013e\u00fa\u010dov\u00e1 pre \u010fal\u0161\u00ed posun v\u00fdskumu v tejto oblasti. Ako sa uv\u00e1dza v na\u0161om \u010dl\u00e1nku, mno\u017estvo d\u00e1tov\u00fdch obmedzen\u00ed brzd\u00ed \u010fal\u0161\u00ed pokrok v NIDS v\u00fdskume a limituje spo\u013eahlivos\u0165 dosiahnut\u00fdch v\u00fdsledkov. V na\u0161om \u010dl\u00e1nku sme tieto obmedzenia detailne diskutovali, navrhli oblasti bud\u00faceho v\u00fdskumu na ich n\u00e1pravu, a uviedli sme dostupn\u00e9 referen\u010dn\u00e9 d\u00e1tov\u00e9 sady za \u00fa\u010delom smerovania bud\u00faceho NIDS v\u00fdskumu k lep\u0161ej robustnosti a spo\u013eahlivosti. Pre\u010d\u00edtajte si na\u0161u prvotn\u00fa verziu \u010dl\u00e1nku na arXiv.org<\/a> pre viac inform\u00e1ci\u00ed (Goldschmidt a Chud\u00e1, 2025).<\/p>\n<\/div>\n\n

\n

<\/p>\n<\/div>\n\n

\n

Referencie<\/h2>\n<\/div>\n\n
\n

Apruzzese, G., Laskov, P., & Johannes. (2023, 06 31). SoK: Pragmatic Assessment of Machine Learning for Network Intrusion Detection. 2023 IEEE 8th European Symposium on Security and Privacy (EuroS&P), 592-614. 10.1109\/EuroSP57164.2023.00042<\/p>\n<\/div>\n\n

\n

Goldschmidt, P., & Chud\u00e1, D. (2025, 02). Network Intrusion Datasets: A Survey, Limitations, and Recommendations. ArXiv. 10.48550\/arXiv.2502.06688<\/p>\n<\/div>\n\n

\n

Petrosyan, A. (2024, December 12). Number of internet users worldwide 2024. Statista. Nav\u0161t\u00edven\u00e9 2025-02-04. www.statista.com\/statistics\/273018\/number-of-internet-users-worldwide\/<\/a> <\/p>\n<\/div>\n\n

\n

Sommer, R., & Paxson, V. (2010). Outside the Closed World: On Using Machine Learning for Network Intrusion Detection. In 2010 IEEE Symposium on Security and Privacy (pp. 305-316). IEEE. 10.1109\/SP.2010.25<\/p>\n<\/div>\n\n

\n

Tieto aktivity boli podporen\u00e9<\/em> Nad\u00e1ciou Pontis<\/em><\/a>, Nada\u010dn\u00fdm Fondom PwC<\/a> pri Nad\u00e1cii Pontis a <\/em>IFT INFORM TECHNOLOGIES, a. s.<\/em><\/a><\/p>\n<\/div>\n\n

\n
\n
\n
\"\"<\/a><\/figure>\n<\/div><\/div>\n<\/div>\n\n
\n
\n
\"\"<\/a><\/figure>\n<\/div><\/div><\/div>\n<\/div>\n\n
\n
<\/div>\n<\/div><\/div>\n<\/div>\n\n
\n

<\/p>\n<\/div>","protected":false},"excerpt":{"rendered":"

V dne\u0161nom svete je internetov\u00e9 pripojenie pova\u017eovan\u00e9 za nutnos\u0165 pre v\u00e4\u010d\u0161inu \u013eud\u00ed. Internet zohr\u00e1va k\u013e\u00fa\u010dov\u00fa \u00falohu pri fungovan\u00ed firiem, online komunik\u00e1cii, vzdel\u00e1van\u00ed, ale aj vo\u013eno\u010dasov\u00fdch aktivit\u00e1ch. Odhaduje sa, \u017ee v…<\/p>\n","protected":false},"author":34,"featured_media":35563,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[81,83,88,520],"tags":[250,405],"class_list":["post-35574","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-data-analytics-for-green-energy-sk","category-news-sk","category-pop-science-sk","category-2025-sk","tag-pop-science-2-sk","tag-cybersecurity-sk"],"acf":[],"yoast_head":"\nChy\u0165me ich v\u0161etky: N\u00e1\u0161 v\u00fdskum v oblasti d\u00e1t pre detekciu \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach - KInIT<\/title>\n<meta name=\"description\" content=\"V dne\u0161nom svete je internetov\u00e9 pripojenie pova\u017eovan\u00e9 za nutnos\u0165 pre v\u00e4\u010d\u0161inu \u013eud\u00ed. Internet zohr\u00e1va k\u013e\u00fa\u010dov\u00fa \u00falohu pri...\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/kinit.sk\/sk\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\/\" \/>\n<meta property=\"og:locale\" content=\"sk_SK\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Chy\u0165me ich v\u0161etky: N\u00e1\u0161 v\u00fdskum v oblasti d\u00e1t pre detekciu \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach - KInIT\" \/>\n<meta property=\"og:description\" content=\"V dne\u0161nom svete je internetov\u00e9 pripojenie pova\u017eovan\u00e9 za nutnos\u0165 pre v\u00e4\u010d\u0161inu \u013eud\u00ed. Internet zohr\u00e1va k\u013e\u00fa\u010dov\u00fa \u00falohu pri...\" \/>\n<meta property=\"og:url\" content=\"https:\/\/kinit.sk\/sk\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\/\" \/>\n<meta property=\"og:site_name\" content=\"KInIT\" \/>\n<meta property=\"article:published_time\" content=\"2025-02-27T03:37:04+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-04-15T12:19:51+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/kinit.sk\/wp-content\/uploads\/2025\/03\/CatchEm-All_blog_feature-.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"628\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Wanda Pribylincova\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@kinit\" \/>\n<meta name=\"twitter:site\" content=\"@kinit\" \/>\n<meta name=\"twitter:label1\" content=\"Autor\" \/>\n\t<meta name=\"twitter:data1\" content=\"Wanda Pribylincova\" \/>\n\t<meta name=\"twitter:label2\" content=\"Predpokladan\u00fd \u010das \u010d\u00edtania\" \/>\n\t<meta name=\"twitter:data2\" content=\"11 min\u00fat\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\\\/\"},\"author\":{\"name\":\"Wanda Pribylincova\",\"@id\":\"https:\\\/\\\/kinit.sk\\\/#\\\/schema\\\/person\\\/64db52a830dcb6d4df386e78e7eb748b\"},\"headline\":\"Chy\u0165me ich v\u0161etky: N\u00e1\u0161 v\u00fdskum v oblasti d\u00e1t pre detekciu \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach\",\"datePublished\":\"2025-02-27T03:37:04+00:00\",\"dateModified\":\"2025-04-15T12:19:51+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\\\/\"},\"wordCount\":2889,\"image\":{\"@id\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/kinit.sk\\\/wp-content\\\/uploads\\\/2025\\\/03\\\/CatchEm-All_blog_feature-.png\",\"keywords\":[\"pop science\",\"cybersecurity\"],\"articleSection\":[\"Data Analytics for Green Energy\",\"News\",\"Pop science\",\"2025\"],\"inLanguage\":\"sk-SK\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\\\/\",\"url\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\\\/\",\"name\":\"Chy\u0165me ich v\u0161etky: N\u00e1\u0161 v\u00fdskum v oblasti d\u00e1t pre detekciu \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach - KInIT\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/kinit.sk\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/kinit.sk\\\/wp-content\\\/uploads\\\/2025\\\/03\\\/CatchEm-All_blog_feature-.png\",\"datePublished\":\"2025-02-27T03:37:04+00:00\",\"dateModified\":\"2025-04-15T12:19:51+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/kinit.sk\\\/#\\\/schema\\\/person\\\/64db52a830dcb6d4df386e78e7eb748b\"},\"description\":\"V dne\u0161nom svete je internetov\u00e9 pripojenie pova\u017eovan\u00e9 za nutnos\u0165 pre v\u00e4\u010d\u0161inu \u013eud\u00ed. Internet zohr\u00e1va k\u013e\u00fa\u010dov\u00fa \u00falohu pri...\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\\\/#breadcrumb\"},\"inLanguage\":\"sk-SK\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/kinit.sk\\\/sk\\\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"sk-SK\",\"@id\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\\\/#primaryimage\",\"url\":\"https:\\\/\\\/kinit.sk\\\/wp-content\\\/uploads\\\/2025\\\/03\\\/CatchEm-All_blog_feature-.png\",\"contentUrl\":\"https:\\\/\\\/kinit.sk\\\/wp-content\\\/uploads\\\/2025\\\/03\\\/CatchEm-All_blog_feature-.png\",\"width\":1200,\"height\":628},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/uvod\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"2025\",\"item\":\"https:\\\/\\\/kinit.sk\\\/sk\\\/category\\\/2025-sk\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Chy\u0165me ich v\u0161etky: N\u00e1\u0161 v\u00fdskum v oblasti d\u00e1t pre detekciu \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/kinit.sk\\\/#website\",\"url\":\"https:\\\/\\\/kinit.sk\\\/\",\"name\":\"KInIT\",\"description\":\"Vyu\u017e\u00edvame v\u00fdskum pre \u013eud\u00ed a priemysel\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/kinit.sk\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"sk-SK\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/kinit.sk\\\/#\\\/schema\\\/person\\\/64db52a830dcb6d4df386e78e7eb748b\",\"name\":\"Wanda Pribylincova\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Chy\u0165me ich v\u0161etky: N\u00e1\u0161 v\u00fdskum v oblasti d\u00e1t pre detekciu \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach - KInIT","description":"V dne\u0161nom svete je internetov\u00e9 pripojenie pova\u017eovan\u00e9 za nutnos\u0165 pre v\u00e4\u010d\u0161inu \u013eud\u00ed. Internet zohr\u00e1va k\u013e\u00fa\u010dov\u00fa \u00falohu pri...","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/kinit.sk\/sk\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\/","og_locale":"sk_SK","og_type":"article","og_title":"Chy\u0165me ich v\u0161etky: N\u00e1\u0161 v\u00fdskum v oblasti d\u00e1t pre detekciu \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach - KInIT","og_description":"V dne\u0161nom svete je internetov\u00e9 pripojenie pova\u017eovan\u00e9 za nutnos\u0165 pre v\u00e4\u010d\u0161inu \u013eud\u00ed. Internet zohr\u00e1va k\u013e\u00fa\u010dov\u00fa \u00falohu pri...","og_url":"https:\/\/kinit.sk\/sk\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\/","og_site_name":"KInIT","article_published_time":"2025-02-27T03:37:04+00:00","article_modified_time":"2025-04-15T12:19:51+00:00","og_image":[{"width":1200,"height":628,"url":"https:\/\/kinit.sk\/wp-content\/uploads\/2025\/03\/CatchEm-All_blog_feature-.png","type":"image\/png"}],"author":"Wanda Pribylincova","twitter_card":"summary_large_image","twitter_creator":"@kinit","twitter_site":"@kinit","twitter_misc":{"Autor":"Wanda Pribylincova","Predpokladan\u00fd \u010das \u010d\u00edtania":"11 min\u00fat"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/kinit.sk\/sk\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\/#article","isPartOf":{"@id":"https:\/\/kinit.sk\/sk\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\/"},"author":{"name":"Wanda Pribylincova","@id":"https:\/\/kinit.sk\/#\/schema\/person\/64db52a830dcb6d4df386e78e7eb748b"},"headline":"Chy\u0165me ich v\u0161etky: N\u00e1\u0161 v\u00fdskum v oblasti d\u00e1t pre detekciu \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach","datePublished":"2025-02-27T03:37:04+00:00","dateModified":"2025-04-15T12:19:51+00:00","mainEntityOfPage":{"@id":"https:\/\/kinit.sk\/sk\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\/"},"wordCount":2889,"image":{"@id":"https:\/\/kinit.sk\/sk\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\/#primaryimage"},"thumbnailUrl":"https:\/\/kinit.sk\/wp-content\/uploads\/2025\/03\/CatchEm-All_blog_feature-.png","keywords":["pop science","cybersecurity"],"articleSection":["Data Analytics for Green Energy","News","Pop science","2025"],"inLanguage":"sk-SK"},{"@type":"WebPage","@id":"https:\/\/kinit.sk\/sk\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\/","url":"https:\/\/kinit.sk\/sk\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\/","name":"Chy\u0165me ich v\u0161etky: N\u00e1\u0161 v\u00fdskum v oblasti d\u00e1t pre detekciu \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach - KInIT","isPartOf":{"@id":"https:\/\/kinit.sk\/#website"},"primaryImageOfPage":{"@id":"https:\/\/kinit.sk\/sk\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\/#primaryimage"},"image":{"@id":"https:\/\/kinit.sk\/sk\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\/#primaryimage"},"thumbnailUrl":"https:\/\/kinit.sk\/wp-content\/uploads\/2025\/03\/CatchEm-All_blog_feature-.png","datePublished":"2025-02-27T03:37:04+00:00","dateModified":"2025-04-15T12:19:51+00:00","author":{"@id":"https:\/\/kinit.sk\/#\/schema\/person\/64db52a830dcb6d4df386e78e7eb748b"},"description":"V dne\u0161nom svete je internetov\u00e9 pripojenie pova\u017eovan\u00e9 za nutnos\u0165 pre v\u00e4\u010d\u0161inu \u013eud\u00ed. Internet zohr\u00e1va k\u013e\u00fa\u010dov\u00fa \u00falohu pri...","breadcrumb":{"@id":"https:\/\/kinit.sk\/sk\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\/#breadcrumb"},"inLanguage":"sk-SK","potentialAction":[{"@type":"ReadAction","target":["https:\/\/kinit.sk\/sk\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\/"]}]},{"@type":"ImageObject","inLanguage":"sk-SK","@id":"https:\/\/kinit.sk\/sk\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\/#primaryimage","url":"https:\/\/kinit.sk\/wp-content\/uploads\/2025\/03\/CatchEm-All_blog_feature-.png","contentUrl":"https:\/\/kinit.sk\/wp-content\/uploads\/2025\/03\/CatchEm-All_blog_feature-.png","width":1200,"height":628},{"@type":"BreadcrumbList","@id":"https:\/\/kinit.sk\/sk\/chytme-ich-vsetky-data-pre-detekciu-utokov-na-pocitacovych-sietach\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/kinit.sk\/sk\/uvod\/"},{"@type":"ListItem","position":2,"name":"2025","item":"https:\/\/kinit.sk\/sk\/category\/2025-sk\/"},{"@type":"ListItem","position":3,"name":"Chy\u0165me ich v\u0161etky: N\u00e1\u0161 v\u00fdskum v oblasti d\u00e1t pre detekciu \u00fatokov na po\u010d\u00edta\u010dov\u00fdch sie\u0165ach"}]},{"@type":"WebSite","@id":"https:\/\/kinit.sk\/#website","url":"https:\/\/kinit.sk\/","name":"KInIT","description":"Vyu\u017e\u00edvame v\u00fdskum pre \u013eud\u00ed a priemysel","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/kinit.sk\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"sk-SK"},{"@type":"Person","@id":"https:\/\/kinit.sk\/#\/schema\/person\/64db52a830dcb6d4df386e78e7eb748b","name":"Wanda Pribylincova"}]}},"_links":{"self":[{"href":"https:\/\/kinit.sk\/sk\/wp-json\/wp\/v2\/posts\/35574","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/kinit.sk\/sk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/kinit.sk\/sk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/kinit.sk\/sk\/wp-json\/wp\/v2\/users\/34"}],"replies":[{"embeddable":true,"href":"https:\/\/kinit.sk\/sk\/wp-json\/wp\/v2\/comments?post=35574"}],"version-history":[{"count":7,"href":"https:\/\/kinit.sk\/sk\/wp-json\/wp\/v2\/posts\/35574\/revisions"}],"predecessor-version":[{"id":36003,"href":"https:\/\/kinit.sk\/sk\/wp-json\/wp\/v2\/posts\/35574\/revisions\/36003"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/kinit.sk\/sk\/wp-json\/wp\/v2\/media\/35563"}],"wp:attachment":[{"href":"https:\/\/kinit.sk\/sk\/wp-json\/wp\/v2\/media?parent=35574"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/kinit.sk\/sk\/wp-json\/wp\/v2\/categories?post=35574"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/kinit.sk\/sk\/wp-json\/wp\/v2\/tags?post=35574"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}