AFOROS: A Low-Cost Wi-Fi-Based Monitoring System for Estimating Occupancy of Public Spaces

Vega-Barbas, Mario; Álvarez-Campana, Manuel; Rivera, Diego; Sanz, Mario Alguacil; Berrocal, Julio

doi:10.3390/s21113863

Cited by 12 publications

(5 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two Probe Requests are considered to be from the same device if their arrival time difference is less than 500 seconds, and the sequence number difference is less than 64. Similarly, a low-cost monitoring system for estimating the occupancy of public spaces is based on the observation of unique fingerprint fields from each smartphone in the Probe Request [67].…”

Section: Passive Techniquesmentioning

confidence: 99%

A Tutorial on Privacy, RCM and Its Implications in WLAN

Ficara,

Garroppo,

Henry

2024

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

The proliferation of Wi-Fi devices has led to the rise of privacy concerns related to MAC Address-based systems used for people tracking and localization across various applications, such as smart cities, intelligent transportation systems, and marketing. These systems have highlighted the necessity for mobile device manufacturers to implement Randomized And Changing MAC address (RCM) techniques as a countermeasure for device identification. In response to the challenges posed by diverse RCM implementations, the IEEE has taken steps to standardize RCM operations through the 802.11aq Task Group (TG). However, while RCM implementation addresses some concerns, it can disrupt services that span both Layer 2 and upper-layers, which were originally designed assuming static MAC addresses. To address these challenges, the IEEE has established the 802.11bh TG, focusing on defining new device identification methods, particularly for Layer 2 services that require pre-association identification. Simultaneously, the IETF launched the MAC Address Device Identification for Network and Application Services (MADINAS) Working Group to investigate the repercussions of RCM on upper-layer services, including the Dynamic Host Configuration Protocol (DHCP).Concurrently, derandomization techniques have emerged to counteract RCM defense mechanisms. The exploration of these techniques has suggested the need for a broader privacy enhancement framework for WLANs that goes beyond simple MAC address randomization. These findings have prompted the inception of the 802.11bi TG, which aims to compile an exhaustive list of potential privacy vulnerabilities and prerequisites for a more private IEEE 802.11 standard.In this context, this tutorial aims to provide insights into the motivations behind RCM, its implementation, and its evolution over the years. It elucidates the influence of RCM on network processes and services. Furthermore, the tutorial delves into the recent progress made within the domains of 802.11bh, 802.11bi, and MADINAS. It offers a thorough analysis of the initial work undertaken by these groups, along with an overview of the relevant research challenges. The tutorial objective is to inspire the research community to explore innovative approaches and solutions that contribute to the ongoing efforts to enhance WLAN privacy through standardization initiatives.

show abstract

Section: Passive Techniquesmentioning

confidence: 99%

A Tutorial on Privacy, RCM and Its Implications in WLAN

Ficara,

Garroppo,

Henry

2024

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

show abstract

“…As mentioned in Section 1.4, a way around this problem that has garnered considerable attention is the so-called de-randomization approach for PRs. In this approach [14][15][16][17][18][19][20][21][22][23][24][25][26], information from digital frame content such as the frame Sequence Number, particular Information Elements (IE), Preferred Network List, and certain time delay measurements derived from these quantities can be analyzed statistically to group together PRs arising from a unique client, thus undoing the effect of the MAC randomization. Though rigorous and often quite effective, a recognized drawback of this approach is that wireless device manufacturers are perpetually on the lookout for such security loopholes, which the next generation of devices is likely to close.…”

Section: Related Workmentioning

confidence: 99%

Tools for Ground-Truth-Free Passive Client Density Mapping in MAC-Randomized Outdoor WiFi Networks

Yang

Ahriz

Denby

2023

Sensors

View full text Add to dashboard Cite

In the past few years, data privacy legislation has hampered the ability of WiFi network operators to count and map client activity for commercial and security purposes. Indeed, since client device MAC devices are now randomized at each transmission, aggregating client activity using management frames such as Probe Requests, as has been common practice in the past, becomes problematic. Recently, researchers have demonstrated that, statistically, client counts are roughly proportional to raw Probe Request counts, thus somewhat alleviating the client counting problem, even if, in most cases, ground truth measurements from alternate sensors such as cameras are necessary to establish this proportionality. Nevertheless, localizing randomized MAC clients at a network site is currently an unsolved problem. In this work, we propose a set of nine tools for extending the proportionality between client counts and Probe Requests to the mapping of client densities in real-world outdoor WiFi networks without the need for ground truth measurements. The purpose of the proposed toolkit is to transform raw, randomized MAC Probe Request counts into a density map calibrated to an estimated number of clients at each position.

show abstract

“…Therefore, one unsupervised learning model is developed, trained and validated per topic (after selecting one of the possible models) and, thus, per the type of data source. Some of these devices have been previously tested in other projects [36,37].…”

Section: Training Datasetmentioning

confidence: 99%

Design and Evaluation of Unsupervised Machine Learning Models for Anomaly Detection in Streaming Cybersecurity Logs

et al. 2022

Self Cite

View full text Add to dashboard Cite

Companies, institutions or governments process large amounts of data for the development of their activities. This knowledge usually comes from devices that collect data from various sources. Processing them in real time is essential to ensure the flow of information about the current state of infrastructure, as this knowledge is the basis for management and decision making in the event of an attack or anomalous situations. Therefore, this article exposes three unsupervised machine learning models based on clustering techniques and threshold definitions to detect anomalies from heterogeneous streaming cybersecurity data sources. After evaluation, this paper presents a case of heterogeneous cybersecurity devices, comparing WSSSE, Silhouette and training time metrics for all models, where K-Means was defined as the optimal algorithm for anomaly detection in streaming data processing. The anomaly detection’s accuracy achieved is also significantly high. A comparison with other research studies is also performed, against which the proposed method proved its strong points.

show abstract

AFOROS: A Low-Cost Wi-Fi-Based Monitoring System for Estimating Occupancy of Public Spaces

Cited by 12 publications

References 41 publications

A Tutorial on Privacy, RCM and Its Implications in WLAN

A Tutorial on Privacy, RCM and Its Implications in WLAN

Tools for Ground-Truth-Free Passive Client Density Mapping in MAC-Randomized Outdoor WiFi Networks

Design and Evaluation of Unsupervised Machine Learning Models for Anomaly Detection in Streaming Cybersecurity Logs

Contact Info

Product

Resources

About