Cybersecurity Defenses: Exploration of CVE Types through Attack Descriptions

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F24%3A00136512" target="_blank" >RIV/00216224:14330/24:00136512 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/SEAA64295.2024.00069" target="_blank" >http://dx.doi.org/10.1109/SEAA64295.2024.00069</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/SEAA64295.2024.00069" target="_blank" >10.1109/SEAA64295.2024.00069</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Cybersecurity Defenses: Exploration of CVE Types through Attack Descriptions

Popis výsledku v původním jazyce

Vulnerabilities in software security can remain undiscovered even after being exploited. Linking attacks to vulnerabilities helps experts identify and respond promptly to the incident. This paper introduces VULDAT, a classification tool using a sentence transformer MPNET to identify system vulnerabilities from attack descriptions. Our model was applied to 100 attack techniques from the ATT&amp;CK repository and 685 issues from the CVE repository. Then, we compare the performance of VULDAT against the other eight state-of-the-art classifiers based on sentence transformers. Our findings indicate that our model achieves the best performance with F1 score of 0.85, Precision of 0.86, and Recall of 0.83. Furthermore, we found 56% of CVE reports vulnerabilities associated with an attack were identified by VULDAT, and 61% of identified vulnerabilities were in the CVE repository.

Název v anglickém jazyce

Cybersecurity Defenses: Exploration of CVE Types through Attack Descriptions

Popis výsledku anglicky

Vulnerabilities in software security can remain undiscovered even after being exploited. Linking attacks to vulnerabilities helps experts identify and respond promptly to the incident. This paper introduces VULDAT, a classification tool using a sentence transformer MPNET to identify system vulnerabilities from attack descriptions. Our model was applied to 100 attack techniques from the ATT&amp;CK repository and 685 issues from the CVE repository. Then, we compare the performance of VULDAT against the other eight state-of-the-art classifiers based on sentence transformers. Our findings indicate that our model achieves the best performance with F1 score of 0.85, Precision of 0.86, and Recall of 0.83. Furthermore, we found 56% of CVE reports vulnerabilities associated with an attack were identified by VULDAT, and 61% of identified vulnerabilities were in the CVE repository.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10200 - Computer and information sciences

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

50th Euromicro Conference Series on Software Engineering and Advanced Applications (SEAA)

ISBN

9798350380262

ISSN

2640-592X

e-ISSN

—

Počet stran výsledku

4

Strana od-do

415-418

Název nakladatele

IEEE

Místo vydání

Not specified

Místo konání akce

Paris, France

Datum konání akce

1. 1. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001413352200059