Wireless device identification with radiometric signatures

By Vladimir Brik, Suman Banerjee, Marco Gruteser, Sangho Oh. ACM/IEEE International Conference on Mobile Computing and Networking, 2008

895 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/40eab4b40829cfd930012d22769b30c29c585cc8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

A Security Credential Management System for V2X Communications (2018, methodology): “, by RF fingerprinting [20] or by deploying a”
AccelPrint: Imperfections of Accelerometers Make Smartphones Trackable (2014, methodology): “Inspired by past work on device fingerprinting [37], [57], [64], where WiFi chipsets were shown to exhibit unique clock skews and frequency offsets, we ask the question: could sensors in today’s smartphones also have unique fingerprints? Hardware imperfections are likely to arise during the manufact”
IoT SENTINEL: Automated Device-Type Identification for Security Enforcement in IoT (2016, background): “specific characteristics such as clock skew [23] or radiofrequency signature [24] can be used to identify a unique network interface card, mostly for rogue wireless Access Point”
A Survey on Wireless Security: Technical Challenges, Recent Advances, and Future Trends (2015, methodology): “This technique was termed as PARADIS [181].”
ProfilIoT: a machine learning approach for IoT device identification based on network traffic analysis (2017, background): “More recently, the authors of [5] leverage passive radio frequency analysis to identify network interface cards (NIC) that transmitted IEEE 802.”
SDDR: Light-Weight, Secure Mobile Encounters (2014, methodology): “To recognize selectively linkable devices, the protocol executes PSI over the devices’ advertised and listen identifier sets.”
Caraoke: An E-Toll Transponder Network for Smart Cities (2015, background): “The closest to our work is [18], which advocates using the CFO of a device as an id for security purposes.”
Brave new world: privacy risks for mobile users (2014, background): “Moreover, analog fingerprinting, whereby a device’s radio is identified by variations during manufacturing, is a viable technique [17], and can be used to track devices, even those that do not leave a trackable signature (such as a MAC address) at the link layer or above.”
A Review of Radio Frequency Fingerprinting Techniques (2020, methodology): “In radiometric techniques, feature extracting can be classified into transient-based and steady state-based features because of the way they treat signals [10].”
Device Fingerprinting in Wireless Networks: Challenges and Opportunities (2015, methodology): “There are several previous literatures adopt this approach as well [5], [6], [11], [13], [14].”
Deep Learning Convolutional Neural Networks for Radio Identification (2018, methodology): “[5] Frequency domain approach [6] PARADIS [7] GTID Supervised (A priori labeling of samples) Unsupervised (Real time grouping of samples)”
Security and Privacy Vulnerabilities of In-Car Wireless Networks: A Tire Pressure Monitoring System Case Study (2010, background): “First, wireless devices are known to present tracking risks through explicit identifiers in protocols [20] or identifiable patterns in waveforms [10].”
DÏoT: A Federated Self-learning Anomaly Detection System for IoT (2018, methodology): “MAC address spoofing can be mitigated using additional techniques for fingerprinting hardware interfaces on wireless [14], [17] and on wired connections [36].”
Zee: zero-effort crowdsourcing for indoor localization (2012, methodology): “In particular, detailed physical layer information has been used to fingerprint both devices [7, 5] and locations [23].”
ORACLE: Optimized Radio clAssification through Convolutional neuraL nEtworks (2018, neutral): “Brik et al [7] SVM based NIC identification”
EnCore: private, context-based communication for mobile social apps (2014, background): “) Finally, we rule out radio fingerprinting attacks, which can identify a device by its unique RF signature [23].”