The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
NLP and ML Synergy: A Novel Approach in Botnet Detection from Sandbox Artifacts
Abstract
The advent of ubiquitous internet access has led to a proliferation of cyber threats. Among these, botnets represent a significant and growing menace to cyber security. Addressing this challenge necessitates the development of potent botnet detection methods. Traditional approaches to botnet detection have predominantly relied on a range of features derived from static or dynamic analysis. This paper presents a novel approach to botnet detection, utilizing Natural Language Processing (NLP), a branch of machine learning (ML), for a more effective analysis. By analyzing behavioral reports through NLP methodologies, including bag-of-words (BoW), BERT, GloVe, and word2vec, we generate rich datasets for ML applications. This unique combination of NLP and ML techniques transforms behavioral data into valuable detection features. Our application of these techniques, reinforced by the XGboost classifier, demonstrates exceptional results in botnet detection, achieving an accuracy of 99.17% and a ROC/AUC score of 0.9995. These findings highlight the critical role of NLP in enhancing feature extraction and the effectiveness of ML in combating botnet threats.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“CMU Logs are appropriate for benchmarking NLP models due to their structured scenarios, supporting Word2Vec with 100% TPR [14,40], but their synthetic bias reduces applicability to real-world settings.”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [40]
In the citing paper
“CMU Logs serve as a benchmark due to their controlled, synthetic nature, enabling reproducible experiments with TPRs reaching 100% in window-based models [14,40].”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [40]
Citations
Cites
Toward developing a systematic approach to generate benchmark datasets for intrusion detection
Shiravi, A., Shiravi, H., Tavallaee, M., & Ghorbani, A. A. (2012) · Computers & Security · doi:10.1016/j.cose.2011.12.012 · Cited by 1,345 · cited 1×
“…identifies three primary challenges in current botnet detection using machine learning (ML): the absence of comprehensive, updated datasets [10]–[12]; robustness of ML model’s against adversarial/ evasive strategies deployed by miscreants; and the limitations of static feature extraction…”
BackgroundThe recent trends in cyber security: A review
Kaur, J., & Ramkumar, K. R. (2021) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2021.01.018 · Cited by 222 · cited 1×
“However, alongside these advancements, the reliance on the Internet has brought forth a spectrum of cyber threats that pose significant challenges to our security and privacy [1], [2].”
BackgroundA Taxonomy of Botnet Behavior, Detection, and Defense
Khattak, S., Ramay, N. R., Khan, K. R., Syed, A. A., & Khayam, S. A. (2014) · IEEE Communications Surveys & Tutorials · doi:10.1109/surv.2013.091213.00134 · Cited by 187 · cited 1×
“Passive techniques involve monitoring and analyzing data from various sources like honeypots, network traffic, and spam records to identify anomalies indicative of botnet activities [8].”
Introduction to Natural Language Processing
Ami Podrebarac, A. (2019) · Fragmentation of the Photographic Image in the Digital Age · doi:10.4324/9781351027946-15 · Cited by 175
Benchmarking datasets for Anomaly-based Network Intrusion Detection: KDD CUP 99 alternatives
Divekar, A., Parekh, M., Savla, V., Mishra, R., & Shirole, M. (2018) · 2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS) · doi:10.1109/cccs.2018.8586840 · Cited by 171 · cited 1×
“…paper identifies three primary challenges in current botnet detection using machine learning (ML): the absence of comprehensive, updated datasets [10]–[12]; robustness of ML model’s against adversarial/ evasive strategies deployed by miscreants; and the limitations of static feature extraction…”
BackgroundAn LSTM-Based Deep Learning Approach for Classifying Malicious Traffic at the Packet Level
Hwang, R.-H., Peng, M.-C., Nguyen, V.-L., & Chang, Y.-L. (2019) · Applied Sciences · doi:10.3390/app9163414 · Cited by 163 · cited 1×
“One notable study by Hwang et al. [18] proposed a methodology based on word embedding and the Long Short-Term Memory (LSTM) network model for classifying packet-based malicious traffic.”
MethodMalware Detection on Highly Imbalanced Data through Sequence Modeling
Oak, R., Du, M., Yan, D., Takawale, H., & Amit, I. (2019) · ACM Workshop on Artificial Intelligence and Security (AISec) · doi:10.1145/3338501.3357374 · Cited by 125 · cited 1×
“Rajvardhan Oak et al. [20] explored ML algorithms for malware classification, employing an LSTM-based strategy.”
MethodA P2P Botnet detection scheme based on decision tree and adaptive multilayer neural networks
Alauthman, M., Aslam, N., Zhang, L., Alasem, R., & Hossain, M. A. (2016) · Neural Computing and Applications · doi:10.1007/s00521-016-2564-5 · Cited by 118 · cited 1×
“In the same way, Alauthaman et al. [25], two well-established datasets, ISOT [26] and ISCX [27], were employed to evaluate their network traffic analysis approach.”
MethodA Study Of Machine Learning Classifiers for Anomaly-Based Mobile Botnet Detection
Feizollah, A., Anuar, N. B., Salleh, R., Amalina, F., Maâ€TMarof, R. R., & Band, S. S. (2013) · Research Explorer (The University of Manchester) · Cited by 96
NLP-based approaches for malware classification from API sequences
Tran, T. K., & Satō, H. (2017) · Asia Pacific Symposium on Intelligent and Evolutionary Systems (IES) · doi:10.1109/iesys.2017.8233569 · Cited by 79 · cited 1×
“By leveraging NLP techniques in ML-based text analyzers, we aim to improve the detection of botnet attacks [13]–[16].”
Method
Research works printed but not linked: 7
- Falliere, 2009, Symantec Security Response
- Prasad, 2020, BOTNET, 43
- 10.5555/3241189.3241275 · doi:10.5555/3241189.3241275
- Song, 2016, Description of kyoto university benchmark data
- 10.1007/s00521-016-2564-5 · DOI
- Faculty of engineering
- 10.1016/j.cose.2011.12.012 · DOI · Paper page
Cited by
A systematic review on insider threat detection using natural language processing
Kundiya, K., & Haribhakta, Y. (2025) · International Journal of Information Security · doi:10.1007/s10207-025-01145-6 · Cited by 9
“Difficulty in scaling with large or diverse datasets in high-traffic environments, potentially leading to delays or missed threats.”
BENCHAMA, A., & Zebbara, K. (2026) · EPJ Web of Conferences · doi:10.1051/epjconf/202638100036
Metadata
- Authors
- Qasim, M., Salman, M., Pedersen, J. M., Masood, A., & Abbas, H.
- Affiliations
- National University of Sciences and Technology (PK)
- Macquarie University (AU)
- Aalborg University (DK)
- Venue
- 2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS)
- Publisher
- IEEE
- Published
- 2024-01-28
- Pages
- 1679-1684
- OpenAlex
- W4392943866
- Semantic Scholar
- 0726c1dc570834722aac21ac0822e783800e8d58
- Cited by
- 2
- References
- 20
- Citations by year
- 2026: 1 · 2025: 1
- FWCI
- 0.75
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS) (publishedVersion)
- VBN Forskningsportal (Aalborg Universitet) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Software › Advanced Malware Detection Techniques
- Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Keywords
- botnet detection, BERT, gloves, Word2Vec, bag-of-words, XGBoost, malware detection
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: NLP and ML Synergy: A Novel Approach in Botnet Detection from Sandbox Artifacts. https://app.cochat.ai/papers/10.1109/icetsis61505.2024.10459415
- The paper
- Qasim, M., Salman, M., Pedersen, J. M., Masood, A., & Abbas, H. (2024). NLP and ML Synergy: A Novel Approach in Botnet Detection from Sandbox Artifacts. 2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS). https://doi.org/10.1109/icetsis61505.2024.10459415
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.