Comparing Transformer-Based Log Anomaly Detection With LLM Explainability In CI/CD Pipelines
With the DevOps setups of today, automating Continuous Integration and Deployment (CI/CD) pipelines is a necessity for achieving rapid software delivery. These pipelines generate enormous logs, which, despite being useful for debugging and monitoring, become cumbersome to analyze manually. In this c...
Uložené v:
| Vydané v: | 2025 Intelligent Methods, Systems, and Applications (IMSA) s. 370 - 375 |
|---|---|
| Hlavní autori: | , , |
| Médium: | Konferenčný príspevok.. |
| Jazyk: | English |
| Vydavateľské údaje: |
IEEE
12.07.2025
|
| Predmet: | |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | With the DevOps setups of today, automating Continuous Integration and Deployment (CI/CD) pipelines is a necessity for achieving rapid software delivery. These pipelines generate enormous logs, which, despite being useful for debugging and monitoring, become cumbersome to analyze manually. In this comparative study, comparison of anomaly detection models on CI/CD pipeline logs, including classical, deep learning, and transformer-based approaches such as LogBERT is performed. An enhanced LogBERT-based classifier i s p resented, incorporating focal loss, grouped anomaly detection, and temperature scaling for better calibration and comparison with other Log anomaly detection models. The evaluation framework includes a feedback loop that allows user-labeled predictions to be reused for iterative retraining. |
|---|---|
| AbstractList | With the DevOps setups of today, automating Continuous Integration and Deployment (CI/CD) pipelines is a necessity for achieving rapid software delivery. These pipelines generate enormous logs, which, despite being useful for debugging and monitoring, become cumbersome to analyze manually. In this comparative study, comparison of anomaly detection models on CI/CD pipeline logs, including classical, deep learning, and transformer-based approaches such as LogBERT is performed. An enhanced LogBERT-based classifier i s p resented, incorporating focal loss, grouped anomaly detection, and temperature scaling for better calibration and comparison with other Log anomaly detection models. The evaluation framework includes a feedback loop that allows user-labeled predictions to be reused for iterative retraining. |
| Author | Al-Aqrabi, Qasem Magdi Solayman, Marwa M. Al-Aqrabi, Hatem Magdi |
| Author_xml | – sequence: 1 givenname: Qasem Magdi surname: Al-Aqrabi fullname: Al-Aqrabi, Qasem Magdi email: qasem.magdi@msa.edu.eg organization: MSA University,Faculty of Computer Science,Cairo,Egypt – sequence: 2 givenname: Hatem Magdi surname: Al-Aqrabi fullname: Al-Aqrabi, Hatem Magdi email: hatem.magdi@msa.edu.eg organization: MSA University,Faculty of Computer Science,Cairo,Egypt – sequence: 3 givenname: Marwa M. surname: Solayman fullname: Solayman, Marwa M. email: mmsolayman@msa.edu.eg organization: MSA University,Faculty of Computer Science,Cairo,Egypt |
| BookMark | eNo1j8FKxDAURSPoQsf5A8H8QGeSvDZplrUzjoUOChbcCEPSvo6BNi1pF_bvVdTF5cBZHLg35NIPHgm552zDOdPb4viayUQBbAQTybfjUnGZXpC1VjoF4AnjqWTX5D0f-tEE58-0CsZP7RB6DNGDmbCh5XCmmR960y10hzPWsxs8fXPzBy3LI91_jp1x3ljXuXmhhad5sc139MWN2DmP0y25ak034fqPK1I97qv8KSqfD0WelZHTMEeWgRT6ZwlYxWvTtIJpo5VCqVNW1xBjbGNUXMciraHBmIFlKK1MZCsMrMjdb9Yh4mkMrjdhOf1_hi8WL1BR |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IL CBEJK RIE RIL |
| DOI | 10.1109/IMSA65733.2025.11167168 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP All) 1998-Present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| EISBN | 9798331501860 |
| EndPage | 375 |
| ExternalDocumentID | 11167168 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IL CBEJK RIE RIL |
| ID | FETCH-LOGICAL-i93t-b03629362953b71cadf209a977e6980cc34e4b4e719428c3de403b0e6b656f2a3 |
| IEDL.DBID | RIE |
| IngestDate | Wed Oct 01 07:05:13 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i93t-b03629362953b71cadf209a977e6980cc34e4b4e719428c3de403b0e6b656f2a3 |
| PageCount | 6 |
| ParticipantIDs | ieee_primary_11167168 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-July-12 |
| PublicationDateYYYYMMDD | 2025-07-12 |
| PublicationDate_xml | – month: 07 year: 2025 text: 2025-July-12 day: 12 |
| PublicationDecade | 2020 |
| PublicationTitle | 2025 Intelligent Methods, Systems, and Applications (IMSA) |
| PublicationTitleAbbrev | IMSA |
| PublicationYear | 2025 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| Score | 1.9146843 |
| Snippet | With the DevOps setups of today, automating Continuous Integration and Deployment (CI/CD) pipelines is a necessity for achieving rapid software delivery. These... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 370 |
| SubjectTerms | Anomaly detection Calibration CI/CD pipelines Context modeling DevOps DevOps automation Explainable AI Feedback learning Pipelines Semantics Software Training Transformer models Transformers Visualization |
| Title | Comparing Transformer-Based Log Anomaly Detection With LLM Explainability In CI/CD Pipelines |
| URI | https://ieeexplore.ieee.org/document/11167168 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NS8MwGA46PHhSceI3OXjN1jRpPo7aORx0Y-DAHYTRpG9nQbuxdcL-vU22KR48eAiEEAg8Obxfz_O-CN3pFCJqNCeUGkl4qnKihOCk_nrNBGOpll4onMjBQI3HergVq3stDAB48hm03NbX8rOZXblUWZu6ogEVah_tSyk3Yq0tZ4sGut3rP98L19-vDvvCqLW7_Wtuijcb3aN_PniMmj8CPDz8Ni0naA_KU_Qab2YGllM82rmbsCAPtR3KcDKb4jqU_0jf17gDlSdYlfilqN5wkvSxo9p5nZSjwq5xr8Rxrx138LCYO0E6LJto1H0cxU9kOxyBFJpVxDjLo92KmJHUplkeBrpGVoLQKrCWceCGg6S6DjAsy4AHzAQgTO3A5WHKzlCjnJVwjrDDDjQLbJCFXIWpErm1kY64CwalEheo6ZCZzDftLyY7UC7_OL9Chw5_lwCl4TVqVIsV3KAD-1kVy8Wt_7QvaRWXUA |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA46BT2pOPG3OXjN1jRpmhy1c6zYjYEFdxBGm75qQbuxdcL-e5tsUzx48BAIIRB47_C9H9-Xh9CtSsCjqeKE0tQnPJE5kUJwUrteMcFYonwrFI78wUCORmq4FqtbLQwAWPIZtMzW9vKziV6YUlmbmqYBFXIb7Xicu3Ql11qztqij2mH_6U6YH_7qxM_1Wpv7vyanWODoHvzzyUPU_JHg4eE3uByhLSiP0UuwmhpYvuJ4E3DCjNzXSJThaPKK62T-I3lf4g5UlmJV4ueiesNR1MeGbGeVUoYMu8RhiYOwHXTwsJgaSTrMmyjuPsRBj6zHI5BCsYqkBnuUWR5LfaqTLHcdVdvWB6GkozXjwFMOPlV1iqFZBtxhqQMirUO43E3YCWqUkxJOETa2A8Uc7WQul24iRa61pzxu0kFfijPUNJYZT1cfYIw3Rjn_4_wG7fXifjSOwsHjBdo3vjDlUOpeokY1W8AV2tWfVTGfXVsHfgF5HJqX |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2025+Intelligent+Methods%2C+Systems%2C+and+Applications%E2%80%8B+%28IMSA%29&rft.atitle=Comparing+Transformer-Based+Log+Anomaly+Detection+With+LLM+Explainability+In+CI%2FCD+Pipelines&rft.au=Al-Aqrabi%2C+Qasem+Magdi&rft.au=Al-Aqrabi%2C+Hatem+Magdi&rft.au=Solayman%2C+Marwa+M.&rft.date=2025-07-12&rft.pub=IEEE&rft.spage=370&rft.epage=375&rft_id=info:doi/10.1109%2FIMSA65733.2025.11167168&rft.externalDocID=11167168 |