Towards a Lightweight Detection System for Cyber Attacks in the IoT Environment Using Corresponding Features
Open accessThe DOI matches its Crossref record; 37 of the 40 references it cites were found in a registry or an index.
Abstract
The application of a large number of Internet of Things (IoT) devices makes our life more convenient and industries more efficient. However, it also makes cyber-attacks much easier to occur because so many IoT devices are deployed and most of them do not have enough resources (i.e., computation and storage capacity) to carry out ordinary intrusion detection systems (IDSs). In this study, a lightweight machine learning-based IDS using a new feature selection algorithm is designed and implemented on Raspberry Pi, and its performance is verified using a public dataset collected from an IoT environment. To make the system lightweight, we propose a new algorithm for feature selection, called the correlated-set thresholding on gain-ratio (CST-GR) algorithm, to select really necessary features. Because the feature selection is conducted on three specific kinds of cyber-attacks, the number of selected features can be significantly reduced, which makes the classifiers very small and fast. Thus, our detection system is lightweight enough to be implemented and carried out in a Raspberry Pi system. More importantly, as the really necessary features corresponding to each kind of attack are exploited, good detection performance can be expected. The performance of our proposal is examined in detail with different machine learning algorithms, in order to learn which of them is the best option for our system. The experiment results indicate that the new feature selection algorithm can select only very few features for each kind of attack. Thus, the detection system is lightweight enough to be implemented in the Raspberry Pi environment with almost no sacrifice on detection performance.
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
“This includes the adoption and deployment of centralized and decentralized hybrid, lightweight [237, 238] and AI-based [239, 240] intrusion detection and intrusion prevention systems, as well as antivirus mechanisms to trigger an automated response through a constant and continuous monitoring.”
From Robotics cyber security: vulnerabilities, attacks, countermeasures, and recommendations (2022) · cites this paper as [240]
Citations
Cites
Wrappers for feature subset selection
Kohavi, R., & John, G. H. (1997) · Artificial Intelligence · doi:10.1016/s0004-3702(97)00043-x · Cited by 8,947 · cited 1×
“Tree-based approaches are simple, and most of these classifiers are lightweight processing architecture.”
BackgroundAn introduction to variable and feature selection
GuyonIsabelle, & ElisseeffAndré (2003) · Journal of Machine Learning Research · doi:10.5555/944919.944968 · Cited by 7,715
Friedman, J., Hastie, T., & Tibshirani, R. (2000) · The Annals of Statistics · doi:10.1214/aos/1016218223 · Cited by 6,884
Kuhn, M., & Johnson, K. (2013) · doi:10.1007/978-1-4614-6849-3 · Cited by 6,788
An Introduction to Variable and Feature Selection.
Guyon, I., & Elisseeff, A. (2003) · Cited by 6,576
A survey on feature selection methods
Chandrashekar, G., & Sahin, F. (2014) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2013.11.024 · Cited by 5,189 · cited 1×
“These are the type of supervised learning methods for prediction of the learning model by growing the tree(s), and these can be applied for regression and classification problems.”
MethodMoustafa, N., & Slay, J. (2015) · 2015 Military Communications and Information Systems Conference (MilCIS) · doi:10.1109/milcis.2015.7348942 · Cited by 4,033 · cited 1×
“These are the type of supervised learning methods for prediction of the learning model by growing the tree(s), and these can be applied for regression and classification problems.”
Method(1998) · Cited by 3,476
Mining high-speed data streams
Domingos, P., & Hulten, G. (2000) · Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/347090.347107 · Cited by 2,185 · cited 2×
“The detection performance of our proposal was examined, including processing time and detection accuracy, for each of the three kinds of attacks.”
MethodInfluentialUsing mutual information for selecting features in supervised neural net learning
Battiti, R. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.298224 · Cited by 2,148 · cited 1×
“These are the type of supervised learning methods for prediction of the learning model by growing the tree(s), and these can be applied for regression and classification problems.”
Method
Research works printed but not linked: 5
- Baker, A.R., and Esler, J. (2007). Snort IDS, IPS Toolkit, Elsevier Inc.. 30 Corporate Dr.
- Da Silva Cardoso, A.M., Lopes, R.F., Teles, A.S., and Magalhaes, F.B.V. (2018, January 17–20). Real-time DDoS detection based on complex event processing for IoT. Proceedings of the Third International Conference on Internet-of-Things Design and Implementation (IoTDI 2018), Orlando, FL, USA.
- Kohavi, R., and Sommerfield, D. (1995, January 20–21). Feature subset selection using the wrapper method: Overfitting and dynamic search space topology. Proceedings of the First International Conference on Knowledge Discovery and Data Mining, Montreal, QC, Canada.
- Karegowda, 2010, Comparative study of Attribute Selection Using Gain Ratio, Int. J. Inf. Technol. Knowl. Knowl. Manag., 2, 271
- Witten, I.H., and Frank, E. (2005). Data Mining. Practical Machine Learning Tools and Technicals with Java Implementations, Elsevier Inc.. [2nd ed.].
Cited by
Items 101–111 of 111
Fatima, M., Rehman, O. M. H., & Rahman, I. M. H. (2024) · International Visualization, Informatics and Technology Conference (IVIT) · doi:10.1109/ivit62102.2024.10692650
“As demonstrated in [7],[13], and [14], evaluating IDS models in terms of resource use is essential.”
BackgroundMethodAn Overview of Security Intelligence in IoT Applications with Learning Approaches
Shukla, T., & Mishra, N. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-69115-7_9
MAP-ECC: Mutual Authentication Protocol for e-Agriculture Using ECC
Pandit, M. K., Ray, S., & Das, P. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-90587-2_8
Yacine, T. M. M., Kandi, M. A., Laraba, A., & Laborde, R. (2025) · International Conference on Federated Learning Technologies and Applications (FLTA) · doi:10.1109/flta67013.2025.11336518
“Numerous articles have been published addressing the problem of security in IoT networks, taking into account limitations in terms of processing and storage capacities, including [5, 7, 8, 9, 10].”
NFD-TRG: Network Flow Detection via Traffic Relationship Graphs with Statistical Feature Embedding
He, M., Zhao, X., & Yang, L. (2025) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom66490.2025.00268
“Soe [24] proposed the Gain Ratio Correlation Set Threshold algorithm as a feature selection algorithm to achieve lightweight IDSs.”
A Voting Ensemble based Learning Model for Malicious Traffic Identification using Internet of Things
Thaseen, I. S., Veronica, B., Islam, S., & Antony, F. (2025) · International Conference on Emerging Innovation and Digital Technology (ICEIDT) · doi:10.1109/iceidt66693.2025.11473434
VijayKumar, B. D., Dhole, A., Deshmukh, P. B., & Singh, M. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae6152
“Furthermore, several approaches remain heavily dependent on predefined attack signatures or patterns, which restricts their adaptability against novel or previously unseen cyber threats [13].”
Ahmad, B., Jamshed, H., Kamal, M. A., Mastoi, Q.-U.-A., Syed, T. A., & Lee, I. E. (2026) · IET Information Security · doi:10.1049/ise2/1301034
Sivakumar, P., & Jeyaselvi, M. (2026) · International Conference on Inventive Research in Computing Applications (ICIRCA) · doi:10.1109/icirca69024.2026.11570157
“It has benchmarked against standalone rule-based and DL-based IDS solutions [4].”
Hnamte, V. (2026) · Measurement Digitalization · doi:10.1016/j.meadig.2026.100060 · Cited by 1
Fotso, J. M. K., Abbo, I., Tchakounté, F., Kue, F. M., Atemkeng, M., Shu, W., & Fachkha, C. (2026) · Data Technologies and Applications · doi:10.1108/dta-01-2025-0032
Metadata
- Authors
- Soe, Y. N., Feng, Y., Santosa, P. I., Hartanto, R., & Sakurai, K.
- Affiliations
- Kyushu University (JP)
- Universitas Gadjah Mada (ID)
- Corresponding author
- Feng, Yaokai
- Santosa, Paulus Insap
- Venue
- Electronics
- Publisher
- MDPI AG
- Published
- 2020-01-11
- Volume
- 9
- Issue
- 1
- Pages
- 144
- ISSN
- 2079-9292 (ISSN-L)
- OpenAlex
- W3000480569
- Cited by
- 110
- References
- 40
- Citations by year
- 2026: 9 · 2025: 14 · 2024: 11 · 2023: 31 · 2022: 19 · 2021: 18 · 2020: 8
- FWCI
- 8.93
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- Locations
- Electronics (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Japan Science and Technology Agency (JP17K00187, JP18K11295)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Physical Sciences › Computer Science › Hardware and Architecture › Network Packet Processing and Optimization
- Physical Sciences › Computer Science › Information Systems › Internet of Things and AI
- Keywords
- intrusion detection, Internet of Things security, feature selection, Raspberry Pi, resource-constrained devices, cyberattack 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
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.