GPT-2C: a parser for honeypot logs using large pre-trained language models
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
Deception technologies like honeypots generate large volumes of log data, which include illegal Unix shell commands used by latent intruders. Several prior works have reported promising results in overcoming the weaknesses of network-level and program-level Intrusion Detection Systems (IDSs) by fussing network traffic with data from honeypots. However, because honeypots lack the plug-in infrastructure to enable real-time parsing of log outputs, it remains technically challenging to feed illegal Unix commands into downstream predictive analytics. As a result, advances on honeypot-based user-level IDSs remain greatly hindered. This article presents a run-time system (GPT-2C) that leverages a large pre-trained language model (GPT-2) to parse dynamic logs generated by a live Cowrie SSH honeypot instance. After fine-tuning the GPT-2 model on an existing corpus of illegal Unix commands, the model achieved 89% inference accuracy in parsing Unix commands with acceptable execution latency.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
DeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning
Du, M., Li, F., Zheng, G., & Srikumar, V. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134015 · Cited by 1,835
Tools and benchmarks for automated log parsing
Zhu, J., He, S., Liu, J., He, P., Xie, Q., Zheng, Z., & Lyu, M. R. (2019) · 2019 IEEE/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) · doi:10.1109/icse-seip.2019.00021 · Cited by 574 · cited 1×
“Owning to the prodigious amount of machine-generated data and the usability problems that emerge, automated log parsing has been studied extensively in recent years [38].”
BackgroundAn intrusion detection and prevention system in cloud computing: A systematic review
Patel, A., Taghavi, M., Bakhtiyari, K., & Celestino Júnior, J. (2013) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2012.08.007 · Cited by 425 · cited 1×
“…IDS performance is hindered by false alarm rates and evasion methods that derive from well-known bottlenecks such as high network traffic, imbalanced data distribution, and difficulty in discovering decision boundaries between benign and malicious software and behaviours [13], [24], [36].”
Background
Research works printed but not linked: 34
- Hassan Artail , Haidar Safa , Malek Sraj , Iyad Kuwatly , and Zaid Al-Masri . A hybrid honeypot framework for improving intrusion detection systems in protecting organizational networks. computers & security, 25(4):274--288 , 2006 . Hassan Artail, Haidar Safa, Malek Sraj, Iyad Kuwatly, and Zaid Al-Masri. A hybrid honeypot framework for improving intrusion detection systems in protecting organizational networks. computers & security, 25(4):274--288, 2006.
- 10.1109/CSCI49370.2019.00035 · DOI
- 10.1002/nem.1867 · DOI
- Falko Dressler , Wolfgang Jaegers , and Reinhard German . Flow-based worm detection using correlated honeypot logs. In Communication in Distributed Systems-15 . ITG/GI Symposium , pages 1 -- 6 . VDE, 2007 . Falko Dressler, Wolfgang Jaegers, and Reinhard German. Flow-based worm detection using correlated honeypot logs. In Communication in Distributed Systems-15. ITG/GI Symposium, pages 1--6. VDE, 2007.
- 10.1109/ICSE.2013.6606586 · DOI · Paper page
- Thomas Wolf et. al. Transformers : State-of-the-art natural language processing . In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations , pages 38 -- 45 , Online , October 2020 . Association for Computational Linguistics. Thomas Wolf et. al. Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 38--45, Online, October 2020. Association for Computational Linguistics.
- Woojin Paik et al. Applying natural language processing (nlp) based metadata extraction to automatically acquire user preferences . In Proceedings of the 1st International Conference on Knowledge Capture, K-CAP '01 , page 116 -- 122 , New York, NY, USA , 2001 . Association for Computing Machinery. Woojin Paik et al. Applying natural language processing (nlp) based metadata extraction to automatically acquire user preferences. In Proceedings of the 1st International Conference on Knowledge Capture, K-CAP '01, page 116--122, New York, NY, USA, 2001. Association for Computing Machinery.
- Javier Franco , Ahmet Aris , Berk Canberk , and A Selcuk Uluagac . A survey of honeypots and honeynets for internet of things, industrial internet of things, and cyber-physical systems. arXiv preprint arXiv:2108.02287 , 2021 . Javier Franco, Ahmet Aris, Berk Canberk, and A Selcuk Uluagac. A survey of honeypots and honeynets for internet of things, industrial internet of things, and cyber-physical systems. arXiv preprint arXiv:2108.02287, 2021. · arXiv
- 10.1109/ICDM.2009.60 · DOI · Paper page
- 10.1109/AICCSA.2010.5587041 · doi:10.1109/aiccsa.2010.5587041
- 10.1002/nem.1923 · DOI
- Samuel Kierszbaum . F1 score in nlp span-based question answering task , 2020 . Samuel Kierszbaum. F1 score in nlp span-based question answering task, 2020.
- 10.1109/ASONAM49781.2020.9381383 · DOI
- Christian Kreibich and Jon Crowcroft . Honeycomb: creating intrusion detection signatures using honeypots. ACM SIGCOMM computer communication review, 34(1):51--56 , 2004 . Christian Kreibich and Jon Crowcroft. Honeycomb: creating intrusion detection signatures using honeypots. ACM SIGCOMM computer communication review, 34(1):51--56, 2004.
- 10.1109/APNOMS.2012.6356055 · doi:10.1109/apnoms.2012.6356055
- 10.3233/JIFS-179659 · DOI
- 10.1007/s40815-020-00947-1 · DOI
- 10.1145/1947940.1948065 · DOI
- 10.1145/1273496.1273576 · DOI · Paper page
- Open AI. Better language models and their implications , 2019 . OpenAI. Better language models and their implications, 2019.
- Adam et. al. Paszke . Pytorch : An imperative style, high-performance deep learning library. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett, editors , Advances in Neural Information Processing Systems 32 , pages 8024 -- 8035 . Curran Associates, Inc. , 2019 . Adam et. al. Paszke. Pytorch: An imperative style, high-performance deep learning library. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett, editors, Advances in Neural Information Processing Systems 32, pages 8024--8035. Curran Associates, Inc., 2019.
- Alec Radford , Jeffrey Wu , Rewon Child , David Luan , Dario Amodei , Ilya Sutskever , Language models are unsupervised multitask learners . OpenAI blog , 1 ( 8 ): 9 , 2019 . Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019.
- Farhan Sadique and Shamik Sengupta . Analysis of attacker behavior in compromised hosts during command and control. arXiv preprint arXiv:2106.04720 , 2021 . Farhan Sadique and Shamik Sengupta. Analysis of attacker behavior in compromised hosts during command and control. arXiv preprint arXiv:2106.04720, 2021. · arXiv
- 10.1109/ICDAR.2017.192 · DOI · Paper page
- Urban Sedlar , Matej Kren , Leon Štefanič Južnič , and Mojca Volk . Cyberlab honeynet dataset , February 2020 . Urban Sedlar, Matej Kren, Leon Štefanič Južnič, and Mojca Volk. Cyberlab honeynet dataset, February 2020.
- 10.1109/CSAC.2003.1254322 · DOI · Paper page
- Candace Suh-Lee . Mining unstructured log messages for security threat detection . 2016 . Candace Suh-Lee. Mining unstructured log messages for security threat detection. 2016.
- Urjita Thakar , Sudarshan Varma , and AK Ramani . Honeyanalyzer-analysis and extraction of intrusion detection patterns & signatures using honeypot . In Proceedings of the Second International Conference on Innovations in Information Technology , pages 1 -- 7 , 2005 . Urjita Thakar, Sudarshan Varma, and AK Ramani. Honeyanalyzer-analysis and extraction of intrusion detection patterns & signatures using honeypot. In Proceedings of the Second International Conference on Innovations in Information Technology, pages 1--7, 2005.
- Olivier Thonnard and Marc Dacier . A framework for attack patterns' discovery in honeynet data. digital investigation, 5:S128--S139 , 2008 . Olivier Thonnard and Marc Dacier. A framework for attack patterns' discovery in honeynet data. digital investigation, 5:S128--S139, 2008.
- 10.1109/ICMLC.2003.1259851 · doi:10.1109/icmlc.2003.1259851
- 10.1109/GIIS.2018.8635603 · DOI
- 10.1109/ICASI.2018.8394581 · DOI
- Shelly Xiaonan Wu and Wolfgang Banzhaf . The use of computational intelligence in intrusion detection systems: A review. Applied soft computing, 10(1):1--35 , 2010 . Shelly Xiaonan Wu and Wolfgang Banzhaf. The use of computational intelligence in intrusion detection systems: A review. Applied soft computing, 10(1):1--35, 2010.
- 10.1109/TIFS.2013.2279800 · DOI
Cited by
Log Parsing with Prompt-based Few-shot Learning
Le, V.-H., & Zhang, H. (2023) · 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE) · doi:10.1109/icse48619.2023.00204 · Cited by 129
“[59] proposed to fine-tune the GPT2 [45] model for log parsing.”
BackgroundLLM in the Shell: Generative Honeypots
Sladić, M., Valeros, V., Catania, C., & Garcia, S. (2024) · 2024 IEEE European Symposium on Security and Privacy Workshops (EuroS&PW) · doi:10.1109/eurospw61312.2024.00054 · Cited by 70
“A similar approach is presented in [8] where a fine-tuned LLM (GPT2C) model is used parsing dynamic logs generated by Cowrie SSH honeypots.”
MethodAli, T., Kostakos, P., & Sheikhi, S. (2026) · Telecom · doi:10.3390/telecom7030073 · Cited by 104
Self-citationBalasubramanian, P., Seby, J., & Kostakos, P. (2023) · 2023 IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386976 · Cited by 22
Self-citationHoneypot's Best Friend? Investigating ChatGPT's Ability to Evaluate Honeypot Logs
Ozkok, M. B., Birinci, B., Cetin, O., Arief, B., & Hernandez-Castro, J. (2024) · European Interdisciplinary Cybersecurity Conference · doi:10.1145/3655693.3655716 · Cited by 8
Metadata
- Authors
- Setianto, F., Tsani, E., Sadiq, F., Domalis, G., Tsakalidis, D., & Kostakos, P.
- Venue
- Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining
- Publisher
- ACM
- Published
- 2021-11-08
- Pages
- 649-653
- OpenAlex
- W4213074563
- Cited by
- 35
- References
- 3
- FWCI
- 5.87
- Type
- conference paper
- Language
- en
- Open access
- bronze
- Funders
- European Commission (101021911,959879)
- Academy of Finland (318927)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.