Skip to main content

Deep Learning-Driven IoT Fingerprinting Devices: Challenges and foresight

Home automation, health services, smart transportation, and Industry 4.0 are just a few of the fields where IoT technology is being used. While the Internet of Things provides several advantages, such as precision and comfort, it also offers several new hazards. IoT devices are subject to numerous cyber threats by attackers due to their low resources; Confidentiality has been identified as a significant obstacle to IoT management. The quantity of linked IoT devices and the design of specific systems frequently compounds the issue.  Using a customisable deep learning approach, we aimed to develop a novel invasion approach to detect the IoT in this Special Issue. DL is regarded as the cornerstone of emerging artificial intelligence.

Several techniques for IoT enabled Device Fingerprinting (DFP) have been presented recently. Sensors are designed in public places for transmission in detector and IoT networks. The range of Internet protocol (IP) detectors for IoTs is considerable, and various suppliers create them without regard for security issues. As a result, the devices must be identified without using the existing identity (ID). If the equipment fingerprint is recorded and verified before enabling users to join the system, DFP can detect illegal users. DFP can also assist in identifying devices in multi-hop wireless connections built on collaboration. DFP is a method of determining a device that does not rely on its networking and other allocated IDs, such as its IP location, MAC (Medium Access Control) address, or IMEI (International Mobile Equipment Identity) numbers. DFP recognises a device basis of data in the packets it sends and receives over the networks. A router receives packets and processes them to retrieve information. DFP rapidly converts the raw data traffic generated by IoT into an input used in deep learning models.

Deep learning adaptability in IoT ecosystems is a big challenge. The data limits of IoT-assisted DFP continue to be a significant barrier to implementing deep learning models. IoT DFP generates a large amount of data of various types and scales, including input from signal frequency and traffic patterns, which will be in multiple forms while coming from the same machine. The need to store and analyze a deep learning model in resource-constrained applications is a constant challenge. Many researchers have used machine learning to address the problem of IoT assisted DFP, but deep learning for IoT assisted DFP needs more attention for further progress. This Special Issue focuses on promoting the transmission of high-quality research with new ideas, methodologies, theories, frameworks, and practices to address the difficulties surrounding IoT enabled Device Fingerprinting with Deep Learning Networks. Solutions that integrate industrial Device Fingerprinting with cutting-edge scientific models based on real-time data and situations are invited.

Papers could consider, but are not limited to:
1.    Internet of Things and Cyber Security: Threats and Solutions
2.    Shaping up Deep learning for Enhanced Security Applications
3.    Insights of IoT enabled Fingerprinting Devices
4.    Deep Learning Models for Fingerprinting Devices: Vision and Mission
5.    Setting the Future of Fingerprinting Devices in Industries
6.    New Age of Deep learning model for Network Transmission
7.    Future of Deep learning in Fingerprinting Devices
8.    Meeting the Challenges of Fingerprinting Devices
9.    Role of Machine learning in Fingerprinting Devices
10.    Insights of Network Connectivity in Fingerprinting Devices
11.    Need for development in Fingerprinting Devices: Futuristic Directions
12.    Recent Trends in Fingerprinting Devices

Provisional Deadline

Submission Deadline: 1st August 2022


Submissions should be original papers and should not be under consideration for publication elsewhere.
Extended versions of papers from relevant conferences and workshops are invited as long as the additional contribution is substantial (at least 30% of new content).
Authors should follow the formatting and submission instructions for the Journal of Cloud Computing at
For more information visit the Springer Nature Information for journal Article Authors pages at
All papers will be peer-reviewed.

There are currently no articles in this collection.