Towards Classifying Devices on the Internet Using Artificial Intelligence

Lavrenovs, Arturs; Graf, Roman; Heinaaro, Kimmo

doi:10.23919/cycon49761.2020.9131713

Cited by 5 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial intelligence (AI) [1] is a new technology driving scientific and technological revolution and industrial transformation, which is divided into three types: weak, strong and super artificial intelligence [2]. The intelligence level of weak artificial intelligence is equivalent to human intelligence, and it is mainly used in some specific fields, such as face recognition, speech recognition, natural language processing, etc.…”

Section: Introductionmentioning

confidence: 99%

Systematic Review and Prospects on Social Risks of Artificial Intelligence— Visual Analysis Based on CiteSpace Knowledge Graph

Zou

2024

View full text Add to dashboard Cite

As artificial intelligence becomes more and more embedded in human society, it also creates social risks. With the help of CiteSpace software, 200 documents related to social risks of artificial intelligence searched from SSCI and SCI journals from 2000 to 2024 were sorted out to sort out the research progress and hot spots. Research shows that there are currently some highly influential scholars and institutions in the field of artificial intelligence social risks, and the number of relevant studies is increasing year by year. Risk resolution and sustainable development issues of artificial intelligence have become important research directions for the continuous development of artificial intelligence.

show abstract

Section: Introductionmentioning

confidence: 99%

Systematic Review and Prospects on Social Risks of Artificial Intelligence— Visual Analysis Based on CiteSpace Knowledge Graph

Zou

2024

View full text Add to dashboard Cite

show abstract

“…Deep learning (DL), an important branch of ML, uses end-to-end learning to automatically learn implicit features from data. For example, Neural Networks (NNs) [35,36] and CNN [37][38][39][40] can automatically learn features from raw traffic data of devices, eliminating manual feature selection. However, a single DL model may not fit all datasets, so ensemble learning models [41] have been proposed and have obtained higher classification accuracy than the individual model [42][43][44][45].…”

Section: Introductionmentioning

confidence: 99%

WYSIWYG: IoT Device Identification Based on WebUI Login Pages

Wang¹,

Li²,

Jing³

et al. 2022

Sensors

View full text Add to dashboard Cite

With the improvement of intelligence and interconnection, Internet of Things (IoT) devices tend to become more vulnerable and exposed to many threats. Device identification is the foundation of many cybersecurity operations, such as asset management, vulnerability reaction, and situational awareness, which are important for enhancing the security of IoT devices. The more information sources and the more angles of view we have, the more precise identification results we obtain. This study proposes a novel and alternative method for IoT device identification, which introduces commonly available WebUI login pages with distinctive characteristics specific to vendors as the data source and uses an ensemble learning model based on a combination of Convolutional Neural Networks (CNN) and Deep Neural Networks (DNN) for device vendor identification and develops an Optical Character Recognition (OCR) based method for device type and model identification. The experimental results show that the ensemble learning model can achieve 99.1% accuracy and 99.5% F1-Score in the determination of whether a device is from a vendor that appeared in the training dataset, and if the answer is positive, 98% accuracy and 98.3% F1-Score in identifying which vendor it is from. The OCR-based method can identify fine-grained attributes of the device and achieve an accuracy of 99.46% in device model identification, which is higher than the results of the Shodan cyber search engine by a considerable margin of 11.39%.

show abstract