A Survey on IoT Profiling, Fingerprinting, and Identification

Safi, Miraqa; Dadkhah, Sajjad; Shoeleh, Farzaneh; Mahdikhani, Hassan; Molyneaux, Heather; Ghorbani, Ali A.

doi:10.1145/3539736

Cited by 27 publications

(6 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The surveys in [18,19] show that supervised, unsupervised, semi-supervised, and deep-learning approaches could all be used for device identification. Supervised ML is used in [10,11,[20][21][22].…”

Section: Related Workmentioning

confidence: 99%

IoT Device Identification Using Unsupervised Machine Learning

Koball,

Rimal,

Wang

et al. 2023

Information

View full text Add to dashboard Cite

Device identification is a fundamental issue in the Internet of Things (IoT). Many critical services, including access control and intrusion prevention, are built on correctly identifying each unique device in a network. However, device identification faces many challenges in the IoT. For example, a common technique to identify a device in a network is using the device’s MAC address. However, MAC addresses can be easily spoofed. On the other hand, IoT devices also include dynamic characteristics such as traffic patterns which could be used for device identification. Machine-learning-assisted approaches are promising for device identification since they can capture dynamic device behaviors and have automation capabilities. Supervised machine-learning-assisted techniques demonstrate high accuracies for device identification. However, they require a large number of labeled datasets, which can be a challenge. On the other hand, unsupervised machine learning can also reach good accuracies without requiring labeled datasets. This paper presents an unsupervised machine-learning approach for IoT device identification.

show abstract

Section: Related Workmentioning

confidence: 99%

IoT Device Identification Using Unsupervised Machine Learning

Koball,

Rimal,

Wang

et al. 2023

Information

View full text Add to dashboard Cite

show abstract

“…In addition to native security features, four main technical solutions can be employed separately or conjointly to prevent the attacks: cryptography [ 41 , 42 ]; Secure Element (SE) [ 43 ]; Intrusion Detection System (IDS) [ 44 , 45 ]; and multilayer signature [ 46 ].…”

Section: Additional Technical Solutionsmentioning

confidence: 99%

A Survey on the Security Challenges of Low-Power Wireless Communication Protocols for Communicating Concrete in Civil Engineerings

Loubet

Alata

Takacs

et al. 2023

Sensors

View full text Add to dashboard Cite

With the increase in low-power wireless communication solutions, the deployment of Wireless Sensor Networks is becoming usual, especially to implement Cyber-Physical Systems. These latter can be used for Structural Health Monitoring applications in critical environments. To ensure a long-term deployment, battery-free and energy-autonomous wireless sensors are designed and can be powered by ambient energy harvesting or Wireless Power Transfer. Because of the criticality of the applications and the limited resources of the nodes, the security is generally relegated to the background, which leads to vulnerabilities in the entire system. In this paper, a security analysis based on an example: the implementation of a communicating reinforced concrete using a network of battery-free nodes; is presented. First, the employed wireless communication protocols are presented in regard of their native security features, main vulnerabilities, and most usual attacks. Then, the security analysis is carried out for the targeted implementation, especially by defining the main hypothesis of the attack and its consequences. Finally, solutions to secure the data and the network are compared. From a global point-of-view, this security analysis must be initiated from the project definition and must be continued throughout the deployment to allow the use of adapted, updatable and upgradable solutions.

show abstract

“…The ensuing output, characterized by heightened precision and accuracy, fuels the system's operational functionalities. To culminate this intricate symphony, the processed data is deftly uploaded to a cloud-based platform, rendering it readily accessible through a dedicated mobile application (Sa et al, 2022). The overarching aim is to empower farmers with the tools and insights required to protect their crops from the capricious vicissitudes of unfavorable weather conditions (Mahony & End eld, 2018).…”

Section: Role Of Machine Learning and Deep Learningmentioning

confidence: 99%

The Impact of IoT and Sensor Integration on Real-Time Weather Monitoring Systems: A Systematic Review

Selvam,

Al-Humairi

2023

Preprint

View full text Add to dashboard Cite

The observation of weather and its impact on human life is undeniable. Weather observations are essential for various sectors, including agriculture, transportation, aviation, and disaster management. Therefore, the collection of data on weather variations is crucial. However, the transient nature of weather variations makes it difficult to collect accurate and real-time data. To overcome this challenge, researchers have developed smart real-time weather monitoring systems integrated with mobile applications. These systems utilize various frameworks, technologies, and techniques, including the Internet of Things (IoT), Arduino, machine learning algorithms, deep learning algorithms, and sensors that measure temperature, humidity, wind speed, and wind direction. These systems provide real-time data on weather conditions, enabling individuals to make informed decisions. The primary objective of this review paper is to critically examine and elaborate on multiple research studies that focus on integrating smart real-time weather monitoring systems with mobile applications. The aim is to understand the techniques, methodologies, and technologies employed in designing and developing such systems. One of the key findings of this review is that integrating smart real-time weather monitoring systems with mobile applications has significant potential to improve weather forecasting and monitoring. For instance, machine learning algorithms can analyze sensor data to identify patterns and accurately predict future weather conditions. Additionally, integrating cloud computing technology in these systems allows for secure data storage, making it accessible to validated individuals from anywhere. In conclusion, integrating smart real-time weather monitoring systems with mobile applications has enormous potential in improving weather forecasting and monitoring. Various frameworks, technologies, and techniques have enabled researchers to develop sophisticated systems that collect accurate and real-time data on weather conditions. These systems significantly affect various sectors, including agriculture, transportation, aviation, and disaster management.

show abstract

A Survey on IoT Profiling, Fingerprinting, and Identification

Cited by 27 publications

References 77 publications

IoT Device Identification Using Unsupervised Machine Learning

IoT Device Identification Using Unsupervised Machine Learning

A Survey on the Security Challenges of Low-Power Wireless Communication Protocols for Communicating Concrete in Civil Engineerings

The Impact of IoT and Sensor Integration on Real-Time Weather Monitoring Systems: A Systematic Review

Contact Info

Product

Resources

About