ALDExA: Automated LLM-Assisted Detection of CVE Exploitation Attempts in Host-Captured Data

Currently, the detection of Common Vulnerabilities and Exposures (CVE) exploitation attempts heavily depends on rule sets manually written for the detection unit. As the number of published CVEs increases each year, there is a need to advance automation efforts for CVE detection. For this purpose, w...

Full description

Saved in:
Bibliographic Details
Main Authors: Niclas Ilg, Maximilian Pfitzenmaier, Dominik Germek, Paul Duplys, Michael Menth
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11018393/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850232369956519936
author Niclas Ilg
Maximilian Pfitzenmaier
Dominik Germek
Paul Duplys
Michael Menth
author_facet Niclas Ilg
Maximilian Pfitzenmaier
Dominik Germek
Paul Duplys
Michael Menth
author_sort Niclas Ilg
collection DOAJ
description Currently, the detection of Common Vulnerabilities and Exposures (CVE) exploitation attempts heavily depends on rule sets manually written for the detection unit. As the number of published CVEs increases each year, there is a need to advance automation efforts for CVE detection. For this purpose, we introduce ALDExA, a framework that fetches CVE information and corresponding exploit codes to identify an exploit string supported by a Large Language Model (LLM). An exploit string is a characteristic element of the analyzed attack and can be monitored during an actual exploitation attempt. As the novelty in this framework lies in the extraction capabilities of the LLM, we furthermore evaluate eight different models towards their performance in identifying a correct exploit string. We evaluate contemporary models in two experiments and find that they are, in up to 81% of the evaluated cases, capable of extracting a correct exploit string from the attack code. In addition, we propose a promising approach to increase the accuracy further and to automatically detect false predictions. As <monospace>ALDExA</monospace> is the first approach to fully automate the CVE detection pipeline, we also discuss remaining limitations and worthwhile areas of future research.
format Article
id doaj-art-c275f8a93a0c4ae99b5587eedc054a8c
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-c275f8a93a0c4ae99b5587eedc054a8c2025-08-20T02:03:13ZengIEEEIEEE Access2169-35362025-01-0113953799539110.1109/ACCESS.2025.357525811018393ALDExA: Automated LLM-Assisted Detection of CVE Exploitation Attempts in Host-Captured DataNiclas Ilg0https://orcid.org/0009-0009-8360-665XMaximilian Pfitzenmaier1Dominik Germek2Paul Duplys3https://orcid.org/0009-0003-4306-9702Michael Menth4https://orcid.org/0000-0002-3216-1015Bosch Research, Renningen, GermanyChair of Communication Networks, University of Tuebingen, Tuebingen, GermanyBosch Research, Hildesheim, GermanyRobert Bosch GmbH, Sector Mobility, Ludwigsburg, GermanyChair of Communication Networks, University of Tuebingen, Tuebingen, GermanyCurrently, the detection of Common Vulnerabilities and Exposures (CVE) exploitation attempts heavily depends on rule sets manually written for the detection unit. As the number of published CVEs increases each year, there is a need to advance automation efforts for CVE detection. For this purpose, we introduce ALDExA, a framework that fetches CVE information and corresponding exploit codes to identify an exploit string supported by a Large Language Model (LLM). An exploit string is a characteristic element of the analyzed attack and can be monitored during an actual exploitation attempt. As the novelty in this framework lies in the extraction capabilities of the LLM, we furthermore evaluate eight different models towards their performance in identifying a correct exploit string. We evaluate contemporary models in two experiments and find that they are, in up to 81% of the evaluated cases, capable of extracting a correct exploit string from the attack code. In addition, we propose a promising approach to increase the accuracy further and to automatically detect false predictions. As <monospace>ALDExA</monospace> is the first approach to fully automate the CVE detection pipeline, we also discuss remaining limitations and worthwhile areas of future research.https://ieeexplore.ieee.org/document/11018393/Common vulnerabilities and exposuresCVE detectionexploit code analysisintrusion detectionlarge language models
spellingShingle Niclas Ilg
Maximilian Pfitzenmaier
Dominik Germek
Paul Duplys
Michael Menth
ALDExA: Automated LLM-Assisted Detection of CVE Exploitation Attempts in Host-Captured Data
IEEE Access
Common vulnerabilities and exposures
CVE detection
exploit code analysis
intrusion detection
large language models
title ALDExA: Automated LLM-Assisted Detection of CVE Exploitation Attempts in Host-Captured Data
title_full ALDExA: Automated LLM-Assisted Detection of CVE Exploitation Attempts in Host-Captured Data
title_fullStr ALDExA: Automated LLM-Assisted Detection of CVE Exploitation Attempts in Host-Captured Data
title_full_unstemmed ALDExA: Automated LLM-Assisted Detection of CVE Exploitation Attempts in Host-Captured Data
title_short ALDExA: Automated LLM-Assisted Detection of CVE Exploitation Attempts in Host-Captured Data
title_sort aldexa automated llm assisted detection of cve exploitation attempts in host captured data
topic Common vulnerabilities and exposures
CVE detection
exploit code analysis
intrusion detection
large language models
url https://ieeexplore.ieee.org/document/11018393/
work_keys_str_mv AT niclasilg aldexaautomatedllmassisteddetectionofcveexploitationattemptsinhostcaptureddata
AT maximilianpfitzenmaier aldexaautomatedllmassisteddetectionofcveexploitationattemptsinhostcaptureddata
AT dominikgermek aldexaautomatedllmassisteddetectionofcveexploitationattemptsinhostcaptureddata
AT paulduplys aldexaautomatedllmassisteddetectionofcveexploitationattemptsinhostcaptureddata
AT michaelmenth aldexaautomatedllmassisteddetectionofcveexploitationattemptsinhostcaptureddata