Towards the Development of a Realistic Multidimensional IoT Profiling Dataset

Dadkhah, Sajjad; Mahdikhani, Hassan; Danso, Priscilla Kyei; Zohourian, Alireza; Truong, Kevin Anh; Ghorbani, Ali A.

doi:10.1109/pst55820.2022.9851966

Cited by 60 publications

(32 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CIC IoT dataset 2022 [186] is a state-of-the-art dataset for intelligent identification and intrusion detection of sixty different IoT devices with different protocols such as IEEE 802.11, Zigbee-based, and Z-Wave. The data contains different stages of each device and different scenarios of the simulated network activity of a smart home.…”

Section: B Iot Time Series Datasetsmentioning

confidence: 99%

Unsupervised Deep Learning for IoT Time Series

Liu

Zhou

Yang

et al. 2023

IEEE Internet Things J.

View full text Add to dashboard Cite

IoT time series analysis has found numerous applications in a wide variety of areas, ranging from health informatics to network security. Nevertheless, the complex spatial temporal dynamics and high dimensionality of IoT time series make the analysis increasingly challenging. In recent years, the powerful feature extraction and representation learning capabilities of deep learning (DL) have provided an effective means for IoT time series analysis. However, few existing surveys on time series have systematically discussed unsupervised DL-based methods. To fill this void, we investigate unsupervised deep learning for IoT time series, i.e., unsupervised anomaly detection and clustering, under a unified framework. We also discuss the application scenarios, public datasets, existing challenges, and future research directions in this area.

show abstract

Section: B Iot Time Series Datasetsmentioning

confidence: 99%

Unsupervised Deep Learning for IoT Time Series

Liu

Zhou

Yang

et al. 2023

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…Device identification aims to classify devices by using feature sets (fingerprints) obtained from network data as input. These features are usually derived from individual packet headers or payloads [1,3,5,10,12], but some studies have also used flow features [7,14]. Although much work has been done in the area of device identification, a number of problems are apparent, including data leakage, overly-specific features, selective device testing, and insufficiently transparent experimental methodology.…”

Section: Related Work On Device Identificationmentioning

confidence: 99%

“…Using a voting method based on feature importance scores, unimportant features are eliminated 4 ⃝. From the remaining features, a genetic algorithm is used to find the best feature combination 5 ⃝. Different machine learning algorithms are tested to find the most appropriate algorithm 6 ⃝.…”

Section: Related Work On Device Identificationmentioning

confidence: 99%

“…In the IoTDevID study, we aimed for a transparent, repeatable and generalisable study, avoiding the pitfalls found in previous studies, such as data leakage, use of identifying features, selective device testing, and non-transparent experiments. We used features derived from packet headers as used in many other studies [1,3,5,12]. However, device identification with individual packets is very difficult due to the high noise.…”

Section: Related Work On Device Identificationmentioning

confidence: 99%

See 1 more Smart Citation

IoTDevID: A Behavior-Based Device Identification Method for the IoT

Kahraman

Just

Lones

2022

IEEE Internet Things J.

View full text Add to dashboard Cite

While the use of the Internet of Things is becoming more and more popular, many security vulnerabilities are emerging with the large number of devices being introduced to the market. In this environment, IoT device identification methods provide a preventive security measure as an important factor in identifying these devices and detecting the vulnerabilities they suffer from. In this study, we present a method that identifies devices in the Aalto dataset using the convolutional neural network (CNN).

show abstract

“…For dataset validation, DT, NB, kNN, SVM, LR, DNN, and GRU algorithms were used. The best results were achieved with DT in all cases, achieving an accuracy of 99.54% for binary classification.• CIC IoT Dataset 2022[42]: Simulating smart home activity, this dataset was created from 60 devices in an isolated IoT sensor network at a laboratory in the Canadian Institute for Cybersecurity (CIC). The IoT network includes WiFi, ZigBee, and Z-Wave devices.…”

mentioning

confidence: 99%

Application of Machine Learning Algorithms for the Validation of a New CoAP-IoT Anomaly Detection Dataset

Vigoya¹,

Pardal²,

Fernández³

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

With the rise in smart devices, the Internet of Things (IoT) has been established as one of the preferred emerging platforms to fulfil their need for simple interconnections. The use of specific protocols such as constrained application protocol (CoAP) has demonstrated improvements in the performance of the networks. However, power-, bandwidth-, and memory-constrained sensing devices constitute a weakness in the security of the system. One way to mitigate these security problems is through anomaly-based intrusion detection systems, which aim to estimate the behaviour of the systems based on their “normal” nature. Thus, to develop anomaly-based intrusion detection systems, it is necessary to have a suitable dataset that allows for their analysis. Due to the lack of a public dataset in the CoAP-IoT environment, this work aims to present a complete and labelled CoAP-IoT anomaly detection dataset (CIDAD) based on real-world traffic, with a sufficient trace size and diverse anomalous scenarios. The modelled data were implemented in a virtual sensor environment, including three types of anomalies in the CoAP data. The validation of the dataset was carried out using five shallow machine learning techniques: logistic regression, naive Bayes, random forest, AdaBoost, and support vector machine. Detailed analyses of the dataset, data conditioning, feature engineering, and hyperparameter tuning are presented. The evaluation metrics used in the performance comparison are accuracy, precision, recall, F1 score, and kappa score. The system achieved 99.9% accuracy for decision tree models. Random forest established itself as the best model, obtaining a 99.9% precision and F1 score, 100% recall, and a Cohen’s kappa statistic of 0.99.

show abstract

Towards the Development of a Realistic Multidimensional IoT Profiling Dataset

Cited by 60 publications

References 17 publications

Unsupervised Deep Learning for IoT Time Series

Unsupervised Deep Learning for IoT Time Series

IoTDevID: A Behavior-Based Device Identification Method for the IoT

Application of Machine Learning Algorithms for the Validation of a New CoAP-IoT Anomaly Detection Dataset

Contact Info

Product

Resources

About