Recovering Cross-Device Connections via Mining IP Footprints with Ensemble Learning

Cao, Xuezhi; Huang, Wenli; Yu, Yong

doi:10.1109/icdmw.2015.129

Cited by 7 publications

(13 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2015, Drawbridge released a challenge [1] to the research community about IP based cross-device tracking. Then, multiple research papers [7,14,19,26,27,33,55,58] on IP based crossdevice tracking were published. Among these methods, IPFootprint [14] achieves state-of-the-art performance.…”

Section: Related Workmentioning

confidence: 99%

“…Specifically, browsing history based tracking utilizes source and destination pairs-e.g., the client IP address and the destination website's domain-of users' browsing records to correlate different devices of the same user. Several browsing history based crossdevice tracking methods [14,36,66] have been proposed. For instance, IPFootprint [14] uses supervised learning to analyze the IPs commonly used by devices.…”

Section: Introductionmentioning

confidence: 99%

“…Several browsing history based crossdevice tracking methods [14,36,66] have been proposed. For instance, IPFootprint [14] uses supervised learning to analyze the IPs commonly used by devices. Zimmeck et al [66] proposed a supervised method that achieves state-of-the-art performance.…”

Section: Introductionmentioning

confidence: 99%

“…First, when labeled device pairs are available, GraphTrack consistently outperforms compared supervised methods. For instance, when 20% users are labeled, GraphTrack outperforms BAT-SU [66] and IPFootprint [14] for mobile-desktop tracking by 0.15 and 0.25 in Accuracy; and for multiple-device tracking by 0.1 and 0.13 in Accuracy, respectively. Second, when no labeled device pairs are available, Graph-Track consistently outperforms compared unsupervised methods.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

GraphTrack: A Graph-based Cross-Device Tracking Framework

Wang¹,

Zhou²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Cross-device tracking has drawn growing attention from both commercial companies and the general public because of its privacy implications and applications for user profiling, personalized services, etc. One particular, wide-used type of cross-device tracking is to leverage browsing histories of user devices, e.g., characterized by a list of IP addresses used by the devices and domains visited by the devices. However, existing browsing history based methods have three drawbacks. First, they cannot capture latent correlations among IPs and domains. Second, their performance degrades significantly when labeled device pairs are unavailable. Lastly, they are not robust to uncertainties in linking browsing histories to devices.We propose GraphTrack, a graph-based cross-device tracking framework, to track users across different devices by correlating their browsing histories. Specifically, we propose to model the complex interplays among IPs, domains, and devices as graphs and capture the latent correlations between IPs and between domains. We construct graphs that are robust to uncertainties in linking browsing histories to devices. Moreover, we adapt random walk with restart to compute similarity scores between devices based on the graphs. GraphTrack leverages the similarity scores to perform cross-device tracking. GraphTrack does not require labeled device pairs and can incorporate them if available. We evaluate GraphTrack on two real-world datasets, i.e., a publicly available mobile-desktop tracking dataset (around 100 users) and a multiple-device tracking dataset (154K users) we collected. Our results show that GraphTrack substantially outperforms the state-of-the-art on both datasets. CCS CONCEPTS• Security and privacy; • Computing methodologies → Machine learning;

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

GraphTrack: A Graph-based Cross-Device Tracking Framework

Wang¹,

Zhou²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…During the Drawbridge Cross-Device Connection competition of the ICDM 2015 conference [2], the participants were provided with a dataset [1] that contained information about some users' devices, cookies, IP addresses and also browsing activity, and were challenged to match cookies with devices and users. This resulted in a number of short papers [10,19,47,48,50,28,78,85] that describe different machine learning approaches followed during the competition for matching devices and cookies. Some of the proposed methods achieved accuracy greater than 90%, and seen from a different point compared to our work, showed that users' devices can be potentially correlated if enough network and device information is available.…”

Section: Cross-device Trackingmentioning

confidence: 99%

Talon: An Automated Framework for Cross-Device Tracking Detection

Solomos,

Ilia,

Ioannidis

et al. 2018

Preprint

View full text Add to dashboard Cite

Although digital advertising fuels much of today's free Web, it typically does so at the cost of online users' privacy, due to the continuous tracking and leakage of users' personal data. In search for new ways to optimize the effectiveness of ads, advertisers have introduced new advanced paradigms such as cross-device tracking (CDT), to monitor users' browsing on multiple devices and screens, and deliver (re)targeted ads in the most appropriate screen. Unfortunately, this practice leads to greater privacy concerns for the end-user.Going beyond the state-of-the-art, we propose a novel methodology for detecting CDT and measuring the factors affecting its performance, in a repeatable and systematic way. This new methodology is based on emulating realistic browsing activity of end-users, from different devices, and thus triggering and detecting cross-device targeted ads. We design and build Talon 1 , a CDT measurement framework that implements our methodology and allows experimentation with multiple parallel devices, experimental setups and settings. By employing Talon, we perform several critical experiments, and we are able to not only detect and measure CDT with average AUC score of 0.78-0.96, but also to provide significant insights about the behavior of CDT entities and the impact on users' privacy. In the hands of privacy researchers, policy makers and end-users, Talon can be an invaluable tool for raising awareness and increasing transparency on tracking practices used by the ad-ecosystem.

show abstract