Monitoring web browsing behavior with differential privacy

Fan, Liyue; Bonomi, Luca; Xiong, Li; Sunderam, Vaidy S.

doi:10.1145/2566486.2568038

Cited by 52 publications

(35 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous work mainly focuses on event-level privacy on finite or infinite streams [14], [16], [17], and user-level privacy on finite streams [5], [7], [15]. Chan et al [16] proposed scheme of p-sum to construct a full binary tree on the sequential data, where each node contains the sum of the sequential data in its subtree, plus noise with scale logarithmic in the length of the sequence.…”

Section: Differential Privacy On Streamsmentioning

confidence: 99%

“…Mir et al [15] considers counters that may also decrease. Fan and Xiong [5], [7] proposed FAST framework for publishing time-series data in a user-level private way. FAST uses sampling and filtering components to reduce the noise; given a specified number of samples, the filtering component predicts the future data and corrects its prior data by noisy samples.…”

Section: Differential Privacy On Streamsmentioning

confidence: 99%

“…We quantitatively evaluate the data utility by the following metrics, Mean of Absolute Error (MAE), Mean of Relative Error (MRE), Mean of Square Error (MSE) and KLdivergence [7]. MAE has been given as Eq.…”

Section: Mae Mre and Msementioning

confidence: 99%

“…1 (c). These statistical answers are expected to be useful for marketing analysis [2], real-time traffic analysis [5], intelligent navigation systems [6], web browsing behavior mining [7] (users' trajectories in the cyberspace)…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Differentially Private Real-Time Data Publishing over Infinite Trajectory Streams

Cao

Yoshikawa

2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYRecent emerging mobile and wearable technologies make it easy to collect personal spatiotemporal data such as activity trajectories in daily life. Publishing real-time statistics over trajectory streams produced by crowds of people is expected to be valuable for both academia and business, answering questions such as "How many people are in Kyoto Station now?" However, analyzing these raw data will entail risks of compromising individual privacy. -Differential Privacy has emerged as a well-known standard for private statistics publishing because of its guarantee of being rigorous and mathematically provable. However, since user trajectories will be generated infinitely, it is difficult to protect every trajectory under -differential privacy. On the other hand, in real life, not all users require the same level of privacy. To this end, we propose a flexible privacy model of -trajectory privacy to ensure every desired length of trajectory under protection of -differential privacy. We also design an algorithmic framework to publish -trajectory private data in real time. Experiments using four real-life datasets show that our proposed algorithms are effective and efficient.

show abstract

Section: Differential Privacy On Streamsmentioning

confidence: 99%

Section: Differential Privacy On Streamsmentioning

confidence: 99%

Section: Mae Mre and Msementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Differentially Private Real-Time Data Publishing over Infinite Trajectory Streams

Cao

Yoshikawa

2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…a user's contribution to the data stream at a single time point, rather than her presence or contribution to the entire series. The works in [25, 13, 14] studied the problem of releasing aggregate time-series with user-level differential privacy. Both works consider temporal correlations of the time-series.…”

Section: Introductionmentioning

confidence: 99%

Differentially Private Histogram Publication for Dynamic Datasets

Xiong

Jiang

et al. 2015

Proceedings of the 24th ACM International on Conference on Information and Knowledge Management

Self Cite

View full text Add to dashboard Cite

Differential privacy has recently become a de facto standard for private statistical data release. Many algorithms have been proposed to generate differentially private histograms or synthetic data. However, most of them focus on “one-time” release of a static dataset and do not adequately address the increasing need of releasing series of dynamic datasets in real time. A straightforward application of existing histogram methods on each snapshot of such dynamic datasets will incur high accumulated error due to the composibility of differential privacy and correlations or overlapping users between the snapshots. In this paper, we address the problem of releasing series of dynamic datasets in real time with differential privacy, using a novel adaptive distance-based sampling approach. Our first method, DSFT, uses a fixed distance threshold and releases a differentially private histogram only when the current snapshot is sufficiently different from the previous one, i.e., with a distance greater than a predefined threshold. Our second method, DSAT, further improves DSFT and uses a dynamic threshold adaptively adjusted by a feedback control mechanism to capture the data dynamics. Extensive experiments on real and synthetic datasets demonstrate that our approach achieves better utility than baseline methods and existing state-of-the-art methods.

show abstract