2021
DOI: 10.48550/arxiv.2107.07818
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Revisiting IoT Device Identification

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
7
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
3
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(7 citation statements)
references
References 0 publications
0
7
0
Order By: Relevance
“…In [18], the study acknowledges the security challenges posed by IoT devices and emphasizes the need for automated management to mitigate these issues. Specifically, the focus is on robustly identifying IoT devices to facilitate the application of appropriate network security policies.…”
Section: Literature Reviewmentioning
confidence: 99%
“…In [18], the study acknowledges the security challenges posed by IoT devices and emphasizes the need for automated management to mitigate these issues. Specifically, the focus is on robustly identifying IoT devices to facilitate the application of appropriate network security policies.…”
Section: Literature Reviewmentioning
confidence: 99%
“…• Serial Number: A unique address to reveal information about an IoT device and the device manufacturer for identification [27].…”
Section: Iot Devices Securable Parameters For This Workmentioning
confidence: 99%
“…Four different tree-based and neural network-based machine learning models (such as Random Forest (RF), 2D CNN, Decision Tree and Fully connected Neural Network) were compared for identifying IoT devices using network behavior [ 4 ]. The finding from the experimental work emphasizes the need of updating the models continuously, as the accuracy degrades over time when the model is tested on data that is outside the training set.…”
Section: Related Workmentioning
confidence: 99%
“…A considerably explored area of research for securing IoT devices is the use of machine learning to detect security issues [ 2 , 3 ]. Most machine learning approaches learn device and traffic features from existing data for detecting security attacks using classification methods [ 4 , 5 ]. Moreover, IoT sensors can provide data that can be effectively used for making real time decisions.…”
Section: Introductionmentioning
confidence: 99%