PP-IDE Behavioural Device Fingerprinting Dataset for Privacy-Preserving Identity Establishment

Fuente: Zenodo
Saved in:
Bibliographic Details
Main Authors: Selvam, Muthupavithran, Wang, shuo, Rui, Liu, Haque, Safwana, Singh, Amit, cui, zhan, Rajarajan, Muttukrishnan
Format: Recurso digital
Language:English
Published: Zenodo 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866901141068972032
author Selvam, Muthupavithran
Wang, shuo
Rui, Liu
Haque, Safwana
Singh, Amit
cui, zhan
Rajarajan, Muttukrishnan
author_facet Selvam, Muthupavithran
Wang, shuo
Rui, Liu
Haque, Safwana
Singh, Amit
cui, zhan
Rajarajan, Muttukrishnan
contents <p>This dataset provides a processed behavioural device-fingerprinting representation designed to support research on privacy-preserving identity establishment and continuous device authentication. The dataset is derived from controlled execution-response measurements collected from 11 Raspberry Pi devices operating under fixed experimental conditions.</p> <p>Measurements originate from 3 Raspberry Pi 3 Model B+ devices and 8 Raspberry Pi 4 Model B devices. Data collection was conducted in a controlled headless execution environment with fixed CPU frequency configuration, CPU core isolation, and reduced scheduling interference to ensure reproducibility of behavioural response signals.</p> <p>Each device was evaluated across 4 CPU cores and multiple reboot cycles. The dataset contains execution-dependent behavioural signals, including:</p> <ul> <li>Temperature-dependent execution responses</li> <li>GPU-related performance counter behaviour</li> <li>CPU hash execution response signals</li> <li>Pseudo-random execution response signals</li> <li>True random number generation: behavioural signals</li> </ul> <p>A comprehensive feature engineering pipeline was applied, incorporating:</p> <ul> <li>Temporal rolling statistical features</li> <li>Exponential moving dynamics</li> <li>Signed behavioural interaction features</li> <li>Robust statistical transformations</li> <li>Behavioural deviation modelling</li> <li>Representation-learning-oriented feature construction</li> </ul> <p>Unlike the CD2A dataset, which utilises a limited handcrafted feature representation focused primarily on QPU frequency behaviour, the PP-IDE dataset provides an expanded behavioural feature space designed to support:</p> <ul> <li>Privacy-preserving federated learning research</li> <li>Behavioural identity establishment modelling</li> <li>Continuous authentication system design</li> <li>Adversarial robustness evaluation</li> <li>Hardware-rooted behavioural fingerprint analysis</li> </ul> <p>Persistent hardware identifiers have been removed and replaced with stable pseudonymous device labels to preserve device-level behavioural consistency while ensuring privacy protection.</p> <p>This dataset is intended for research in behavioural device authentication, privacy-preserving machine learning, federated behavioural modelling, and security evaluation of embedded and IoT systems.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_19202451
institution Zenodo
language eng
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle PP-IDE Behavioural Device Fingerprinting Dataset for Privacy-Preserving Identity Establishment
Selvam, Muthupavithran
Wang, shuo
Rui, Liu
Haque, Safwana
Singh, Amit
cui, zhan
Rajarajan, Muttukrishnan
Behavioural Device Fingerprinting
Privacy-Preserving Identity Establishment
Federated Learning for IoT Security
Differential Privacy in Device Authentication
IoT Device Security
Temporal Behaviour Modelling
Reboot Stability Analysis
Performance Counter Fingerprinting
Device Behaviour Modelling
<p>This dataset provides a processed behavioural device-fingerprinting representation designed to support research on privacy-preserving identity establishment and continuous device authentication. The dataset is derived from controlled execution-response measurements collected from 11 Raspberry Pi devices operating under fixed experimental conditions.</p> <p>Measurements originate from 3 Raspberry Pi 3 Model B+ devices and 8 Raspberry Pi 4 Model B devices. Data collection was conducted in a controlled headless execution environment with fixed CPU frequency configuration, CPU core isolation, and reduced scheduling interference to ensure reproducibility of behavioural response signals.</p> <p>Each device was evaluated across 4 CPU cores and multiple reboot cycles. The dataset contains execution-dependent behavioural signals, including:</p> <ul> <li>Temperature-dependent execution responses</li> <li>GPU-related performance counter behaviour</li> <li>CPU hash execution response signals</li> <li>Pseudo-random execution response signals</li> <li>True random number generation: behavioural signals</li> </ul> <p>A comprehensive feature engineering pipeline was applied, incorporating:</p> <ul> <li>Temporal rolling statistical features</li> <li>Exponential moving dynamics</li> <li>Signed behavioural interaction features</li> <li>Robust statistical transformations</li> <li>Behavioural deviation modelling</li> <li>Representation-learning-oriented feature construction</li> </ul> <p>Unlike the CD2A dataset, which utilises a limited handcrafted feature representation focused primarily on QPU frequency behaviour, the PP-IDE dataset provides an expanded behavioural feature space designed to support:</p> <ul> <li>Privacy-preserving federated learning research</li> <li>Behavioural identity establishment modelling</li> <li>Continuous authentication system design</li> <li>Adversarial robustness evaluation</li> <li>Hardware-rooted behavioural fingerprint analysis</li> </ul> <p>Persistent hardware identifiers have been removed and replaced with stable pseudonymous device labels to preserve device-level behavioural consistency while ensuring privacy protection.</p> <p>This dataset is intended for research in behavioural device authentication, privacy-preserving machine learning, federated behavioural modelling, and security evaluation of embedded and IoT systems.</p>
title PP-IDE Behavioural Device Fingerprinting Dataset for Privacy-Preserving Identity Establishment
topic Behavioural Device Fingerprinting
Privacy-Preserving Identity Establishment
Federated Learning for IoT Security
Differential Privacy in Device Authentication
IoT Device Security
Temporal Behaviour Modelling
Reboot Stability Analysis
Performance Counter Fingerprinting
Device Behaviour Modelling
url https://doi.org/10.5281/zenodo.19202451