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.”
MethodKoroniotis, N., Moustafa, N., Sitnikova, E., & Turnbull, B. (2019) · Future Generation Computer Systems · doi:10.1016/j.future.2019.05.041 · Cited by 1,983
Mining time-changing data streams
Hulten, G., Spencer, L., & Domingos, P. (2001) · Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/502512.502529 · Cited by 1,748
A Survey on IoT Security: Application Areas, Security Threats, and Solution Architectures
Hassija, V., Chamola, V., Saxena, V., Jain, D., Goyal, P., & Sikdar, B. (2019) · IEEE Access · doi:10.1109/access.2019.2924045 · Cited by 1,396 · cited 2×
“DDoS attacks can occur in both the network layer and the application layer in the IoT environment [9].”
BackgroundLandwehr, N., Hall, M., & Frank, E. (2005) · Machine Learning · doi:10.1007/s10994-005-0466-3 · Cited by 1,214 · cited 1×
“As mentioned above, a part of the original dataset was selected for our experiment so that the hardware could deal with it even when all the original features were used with the tree-based classifiers.”
MethodHow Many Trees in a Random Forest?
Oshiro, T. M., Perez, P. S., & Baranauskas, J. A. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-31537-4_13 · Cited by 912 · cited 1×
“A comparison of F-measure of J48, VFDT, LMT, and RF between the cases using all features or using CST-GR selected features for each kind of attack.”
MethodGeneration of a new IDS test dataset: Time to retire the KDD collection
Creech, G., & Hu, J. (2013) · 2013 IEEE Wireless Communications and Networking Conference (WCNC) · doi:10.1109/wcnc.2013.6555301 · Cited by 320 · cited 1×
“Using the Using the”
Detection of sinkhole attacks for supporting secure routing on 6LoWPAN for Internet of Things
Cervantes, C., Poplade, D., Nogueira, M., & Santos, A. (2015) · 2015 IFIP/IEEE International Symposium on Integrated Network Management (IM) · doi:10.1109/inm.2015.7140344 · Cited by 243 · cited 1×
“We used the well-known tree-based classifiers J48, Hoeffding tree (VFDT), logistic model tree (LMT), and random forest (RF) for implementing our detection system.”
MethodA Host-Based Intrusion Detection and Mitigation Framework for Smart Home IoT Using OpenFlow
Nobakht, M., Sivaraman, V., & Boreli, R. (2016) · 2016 11th International Conference on Availability, Reliability and Security (ARES) · doi:10.1109/ares.2016.64 · Cited by 237 · cited 2×
“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.”
BackgroundMethodShah, S. A. R., & Issac, B. (2018) · Future Generation Computer Systems · doi:10.1016/j.future.2017.10.016 · Cited by 224 · cited 2×
“Although anomaly detection systems may be effective for new kinds of attacks, the problem of the high false positive rate is one of the main challenges [6,7].”
BackgroundMethodAshari, A., Paryudi, I., & Min, A. (2013) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2013.041105 · Cited by 179 · cited 2×
“The training dataset was divided into three groups according to the three kinds of attacks.”
MethodPulse: an adaptive intrusion detection for the internet of things
Anthi, E., Williams, L., & Burnap, P. (2018) · Living in the Internet of Things: Cybersecurity of the IoT - 2018 · doi:10.1049/cp.2018.0035 · Cited by 143 · cited 1×
“A novel IDS for the IoT environment was proposed using not only ML methodologies, but also a rule-based architecture [17].”
MethodA Lightweight Perceptron-Based Intrusion Detection System for Fog Computing
Sudqi Khater, B., Abdul Wahab, A. W. B., Idris, M. Y. I. B., Abdulla Hussain, M., & Ahmed Ibrahim, A. (2019) · Applied Sciences · doi:10.3390/app9010178 · Cited by 127
An Automata Based Intrusion Detection Method for Internet of Things
Fu, Y., Yan, Z., Cao, J. P., Koné, O., & Cao, X. (2017) · Mobile Information Systems · doi:10.1155/2017/1750637 · Cited by 126 · cited 1×
“J48 (C4.5) is the descendant of ID3, and it is one of the decision tree generation algorithms developed by Ross Quinlan.”
BackgroundAn Introduction to Feature Selection
Kühn, M., & Johnson, K. (2013) · Springer eBooks · doi:10.1007/978-1-4614-6849-3_19 · Cited by 117 · cited 1×
“This algorithm can also work well with nominal and numerical features.”
BackgroundRPiDS: Raspberry Pi IDS — A Fruitful Intrusion Detection System for IoT
Sforzin, A., Mármol, F. G., Conti, M., & Bohli, J.-M. (2016) · IEEE Smart World Congress and International Conferences on Ubiquitous Intelligence & Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People (SmartWorld/UIC/ATC/ScalCom/CBDCom/IoP) · doi:10.1109/uic-atc-scalcom-cbdcom-iop-smartworld.2016.0080 · Cited by 112 · cited 3×
“The leaf nodes represent classes or class attributes.”
BackgroundMethodTowards Trust and Friendliness Approaches in the Social Internet of Things
Amin, F., Ahmad, A., & Choi, G. S. (2019) · Applied Sciences · doi:10.3390/app9010166 · Cited by 75 · cited 1×
“We also observe that, without the help of the CST-GR algorithm, Raspberry Pi cannot handle the entire dataset used in our experiments.”
MethodSoe, Y. N., Feng, Y., Santosa, P. I., Hartanto, R., & Sakurai, K. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-15032-7_39 · Cited by 67 · 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.”
MethodSelf-citationHaider, W., Creech, G., Xie, Y., & Hu, J. (2016) · Future Internet · doi:10.3390/fi8030029 · Cited by 61 · cited 3×
“There were 10,263 botnets hosted in different IoT devices identified in 2018 [3].”
BackgroundMethodInfluentialFeature Selection for Machine Learning-Based Early Detection of Distributed Cyber Attacks
Feng, Y., Akiyama, H., Lu, L., & Sakurai, K. (2018) · IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · doi:10.1109/dasc/picom/datacom/cyberscitec.2018.00040 · Cited by 44 · cited 1×
“The irrelevant features or redundant information should be eradicated [28,29] because of such features that can not only raise the computation cost, but also deteriorate the detection performance [30].”
BackgroundSelf-citationA survey on Botnet: Classification, detection and defense
Amini, P., Araghizadeh, M. A., & Azmi, R. (2015) · International Electronics Symposium (IES) · doi:10.1109/elecsym.2015.7380847 · Cited by 38 · cited 1×
“The botnet attacks can be classified into DDoS, pushing, identify theft, information leakage, and keylogging [8].”
BackgroundAn efficient approach to prevent Battery Exhaustion Attack on BLE-based mesh networks
Guo, Z., Harris, I. G., Jiang, Y., & Tsaur, L.-F. (2017) · 2012 International Conference on Computing, Networking and Communications (ICNC) · doi:10.1109/iccnc.2017.7876092 · Cited by 25 · cited 2×
“Some studies [15,16] addressed specific types of threats targeting IoT devices.”
BackgroundRaspberry Pi as an Intrusion Detection System, a Honeypot and a Packet Analyzer
Tripathi, S., & Kumar, R. (2018) · International Conference on Computational Techniques, Electronics and Mechanical Systems (CTEMS) · doi:10.1109/ctems.2018.8769135 · Cited by 25 · cited 1×
“[27] Misuse-based Pi 3-B Snort ICMP ping, brute-force Conventional”
Pi-IDS: evaluation of open-source intrusion detection systems on Raspberry Pi 2
Kyaw, A. K., Chen, Y., & Joseph, J. (2015) · doi:10.1109/infosec.2015.7435523 · Cited by 23 · cited 1×
“It uses information gain for splitting criteria to construct the tree.”
The security of RFID readers with IDS/IPS solution using Raspberry Pi
Zitta, T., Neruda, M., & Vojtěch, L. (2017) · International Carpathian Control Conference · doi:10.1109/carpathiancc.2017.7970418 · Cited by 20 · cited 3×
“Thus, they cannot detect new kinds of attacks and new variants of known attacks [5].”
BackgroundMethodInfluentialTracking intruders in IoT networks by means of DNS traffic analysis
von Sperling, T. L., Filho, F. L. D. C., de Sousa, R. T., Martins, L. M. C. E., & Rocha, R. L. (2017) · Workshop on Communication Networks and Power Systems (WCNPS) · doi:10.1109/wcnps.2017.8252938 · Cited by 18 · cited 2×
“The study [22] also proposed an IDS solution on an IoT router for verifying the domain name system (DNS) traffic generated from IoT devices.”
MethodFree and open source intrusion detection systems: A study
Tirumala, S. S., Sathu, H., & Sarrafzadeh, A. (2015) · International Conference on Machine Learning and Cybernetics · doi:10.1109/icmlc.2015.7340923 · Cited by 17 · cited 1×
“In the test phase shown in Figure 3, the necessary features for all the classifiers are extracted from the test data.”
MethodPerformance Comparison of Open Source IDSs via Raspberry Pi
Coşar, M., & Kıran, H. E. (2018) · doi:10.1109/idap.2018.8620784 · Cited by 8 · cited 1×
“[26] Misuse-based Snort, Suricata SYN flood, Smurf, UDP flood Conventional”
Background
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
Abdullahi, M., Baashar, Y., Alhussian, H., Alwadain, A., Aziz, N., Capretz, L. F., & Abdulkadir, S. J. (2022) · Electronics · doi:10.3390/electronics11020198 · Cited by 361
Kumar, P., Kumar, R., Srivastava, G., Gupta, G. P., Tripathi, R., Gadekallu, T. R., & Xiong, N. N. (2021) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2021.3089435 · Cited by 360
Robotics cyber security: vulnerabilities, attacks, countermeasures, and recommendations
Yaacoub, J.-P. A., Noura, H. N., Salman, O., & Chehab, A. (2022) · International Journal of Information Security · doi:10.1007/s10207-021-00545-8 · Cited by 320
Hybrid Deep Learning for Botnet Attack Detection in the Internet-of-Things Networks
Popoola, S. I., Adebisi, B., Hammoudeh, M., Gui, G., & Gacanin, H. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3034156 · Cited by 248
“[66] did not consider the DoS attack scenario.”
BackgroundKumar, P., Gupta, G. P., & Tripathi, R. (2021) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2020.101954 · Cited by 208
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.