IoT Device Identification via Network-Flow Based Fingerprinting and Learning

Hamad, Salma Abdalla; Zhang, Wei Emma; Sheng, Quan Z.; Nepal, Surya

doi:10.1109/trustcom/bigdatase.2019.00023

Cited by 64 publications

(31 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 4 provides a comparison of our approach with others. It shows that our brand and model identification accuracy can achieve 90.5% and 92.3% respectively only by top five protocol probes in the optimal multi-protocol probe sequence, superior to the firmware identification [15] and type identification [31,32]. Although our performance is less than the type identification of 95%, our identification fineness is far higher than type identification method.…”

Section: Value Iteration Algorithmmentioning

confidence: 80%

A Time-efficient Multi-Protocol Probe Scheme for Fine-grain IoT Device Identification

Chen

et al. 2020

Sensors

View full text Add to dashboard Cite

Internet of Things (IoT) devices connected to the Internet are exploding, which poses a significant threat for their management and security protection. IoT device identification is a prerequisite for discovering, monitoring, and protecting these devices. Although we can identify the device type easily through grabbing protocol banner information, both brand and model of different types of device are various and diverse. We should therefore utilize multi-protocol probes to improve the fineness of device identification and obtain the corresponding brand and model. However, it is still a challenge to balance between the multi-protocol probe overhead and the identification fineness. To solve this problem, we proposed a time-efficient multi-protocol probe scheme for fine-grain devices identification. We first adopted the concept of reinforcement learning to model the banner-based device identification process into a Markov decision process (MDP). Through the value iteration algorithm, an optimal multi-protocol probe sequence is generated for a type-known IoT device, and then the optimal multi-protocol probes sequence segment is extracted based on the gain threshold of identification accuracy. We took 132,835 webcams as the sample data to experiment. The experimental results showed that our optimal multi-protocol probes sequence segment could reduce the identification time of webcams’ brand and model by 50.76% and achieve the identification accuracy of 90.5% and 92.3% respectively. In addition, we demonstrated that our time-efficient optimal multi-protocol probe scheme could also significantly improve the identification efficiency of other IoT devices, such as routers and printers.

show abstract

Section: Value Iteration Algorithmmentioning

confidence: 80%

A Time-efficient Multi-Protocol Probe Scheme for Fine-grain IoT Device Identification

Chen

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…A multi-stage classification algorithm was developed based on the network activity, demonstrating its ability to identify particular IoT devices [ 24 ]. A device identification approach was proposed where packet sequences from high-level network-flow traffic data were analyzed using supervised ML techniques to extract distinct flow-based features to create device fingerprinting [ 25 ]. The proposed approach was able to automatically identify device types in the white list and the individual device instances in the IoT network.…”

Section: Literature Reviewmentioning

confidence: 99%

“…We employ the One-Vs-Rest classifier also called the One-Vs-All classifier, which is a multi-class classifier training one classifier per class. As a result, N classifiers will be created for N classes [ 25 ]. To achieve this, any

(i.e., a sequence of packets) captured on the server will be labeled either as 1 or 0 in n profiles (n = number of devices).…”

Section: Enforcementmentioning

confidence: 99%

Automated IoT Device Identification Based on Full Packet Information Using Real-Time Network Traffic

Yousefnezhad

Malhi

Främling

2021

Sensors

View full text Add to dashboard Cite

In an Internet of Things (IoT) environment, a large volume of potentially confidential data might be leaked from sensors installed everywhere. To ensure the authenticity of such sensitive data, it is important to initially verify the source of data and its identity. Practically, IoT device identification is the primary step toward a secure IoT system. An appropriate device identification approach can counteract malicious activities such as sending false data that trigger irreparable security issues in vital or emergency situations. Recent research indicates that primary identity metrics such as Internet Protocol (IP) or Media Access Control (MAC) addresses are insufficient due to their instability or easy accessibility. Thus, to identify an IoT device, analysis of the header information of packets by the sensors is of imperative consideration. This paper proposes a combination of sensor measurement and statistical feature sets in addition to a header feature set using a classification-based device identification framework. Various machine Learning algorithms have been adopted to identify different combinations of these feature sets to provide enhanced security in IoT devices. The proposed method has been evaluated through normal and under-attack circumstances by collecting real-time data from IoT devices connected in a lab setting to show the system robustness.

show abstract

“…Also, it uses for solving everyday problems, in industry and agriculture, in VANET networks, and flying sensor networks. Hamad (Hamad et al, 2019) illustrated that the IoT system identifies challenges by processing a series of network packets. the proposed system tracks the network flow data and extracts specific features to establish a fingerprint for each device in the network.…”

Section: Introductionmentioning

confidence: 99%

“…The proposed approach can automatically recognize white-listed device types and unknown devices with abnormal behavior connecting to the network by constraining and enforcing privileges rules for IoT device communications. They achieve 90.3% accuracy, as unknown devices are detected with limited overhead (Hamad et al, 2019). Jo and Kim (Jo and Kim, 2019) adopted an architecture for integrating augmented reality (AR) technology with the Internet of Things for a better shopping experience.…”

Section: Introductionmentioning

confidence: 99%

Expert system for identifying and analyzing the IoT devices using Augmented Reality Approach

Alkishri

Al-Bahri

2021

airdj

View full text Add to dashboard Cite

Biometrics In conjunction with the new development of the Internet of Things (IoT), augmented reality (AR) systems are evolving to visualize 3D virtual models of the real world into an intelligent and interactive virtual reality environment that facilitates physical identification of objects and defines their specifications efficiently. The integration between AR and IoT in a complementary way helps identify network-related items' specifications and interact with the Internet of Things more efficiently. An identity is a dedicated, publicly known attribute or set of names for an individual device. Typically, identifiers operate within a specific area or network, making it difficult to identify things globally. This paper explores the use of Augmented Reality (AR) Technology for identifying devices and displaying relevant information about the device to the user. Based on the developed model network, the developed system of identification of IoT devices was tested. Also, the traffic generated by the AR device when generating requests to the organization server was investigated. According to the test results, the system is undemanding to the main network indicators. The system-generated traffic is self-similar. The test results show that the server software can solve the problems of identifying IoT devices through interaction with augmented reality devices.

show abstract

IoT Device Identification via Network-Flow Based Fingerprinting and Learning

Cited by 64 publications

References 12 publications

A Time-efficient Multi-Protocol Probe Scheme for Fine-grain IoT Device Identification

A Time-efficient Multi-Protocol Probe Scheme for Fine-grain IoT Device Identification

Automated IoT Device Identification Based on Full Packet Information Using Real-Time Network Traffic

Expert system for identifying and analyzing the IoT devices using Augmented Reality Approach

Contact Info

Product

Resources

About