Achieving correlated differential privacy of big data publication

Lv, Denglong; Zhu, Shibing

doi:10.1016/j.cose.2018.12.017

Cited by 24 publications

(17 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Information Theory Approach [13] Statistical Correlation Analysis Method [15] Divide and Conquer Technique for Correlated Big Data Privacy [16] Exhaustive Combinations, Dependent DP [17] Concept of Privacy Leakage with Time [18]…”

Section: Sensitivity Analysis Approachmentioning

confidence: 99%

“…It was the existence of correlation in the datasets [11][9] [12]. Initial researches around DP ignored its existence and regarded data as IID but later researches showed that real datasets often had high correlation among them and hence researches including data correlation became primarily significant [13][14] [15]. Many researchers have studied the adverse effects of data correlation on data privacy and various approaches have been proposed by different researchers in their published works to deal with the issue of privacy threat due to the existence of data correlation in datasets.…”

Section: Introductionmentioning

confidence: 99%

“…The correlation analysis techniques and feature selection techniques used were not good enough to study complex relationships. 13 Correlated differential privacy of big data publication [13] Proposed use of Divide and conquer approach along with machine learning, Used correlated big datasets.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning Concepts for Correlated Big Data Privacy

Biswas¹,

Khare²,

Agrawal³

et al. 2021

Preprint

View full text Add to dashboard Cite

With data becoming a salient asset worldwide, dependence within data kept on growing, hence the real world datasets that one works upon in today's time are highly correlated. Since the past few years, researchers have given attention to this aspect of data privacy and found that where there exists a correlation among data, the existing privacy guarantees could not be assured with existing privacy algorithms. The privacy guarantees provided by existing algorithms were enough when there existed no relation between data in the datasets. Hence, by keeping the existence of data correlation into account, there is a dire need, to reconsider the privacy algorithms. Some of the research have considered to utilize a well known machine learning concept, i.e., Data Correlation Analysis to understand the relationship between data in a better way. This has given some promising results as well. Though its less but still a considerable amount of research has been done for correlated data privacy. But correlated big data privacy is very less explored. The real world datasets that are worked upon, are often large in size (technologically termed as big data) and house a high amount of data correlation. Hence, there is a grave need to understand and propose solutions for correlated big data privacy.

show abstract

Section: Sensitivity Analysis Approachmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Concepts for Correlated Big Data Privacy

Biswas¹,

Khare²,

Agrawal³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Dwork et al [5] firstly propose the differential privacy to rigorously protect individual privacy. en, many works [16][17][18][19][20] apply it to the static dataset, which will not be updated in the future.…”

Section: Related Workmentioning

confidence: 99%

Differentially Private Web Browsing Trajectory over Infinite Streams

Liu

Guo

Tan

et al. 2021

Security and Communication Networks

View full text Add to dashboard Cite

Nowadays, a lot of data mining applications, such as web traffic analysis and content popularity prediction, leverage users’ web browsing trajectories to improve their performance. However, the disclosure of web browsing trajectory is the most prominent issue. A novel privacy model, named Differential Privacy, is used to rigorously protect user’s privacy. Some works have applied this privacy model to spatial-temporal streams. However, these works either protect the users’ activities in different places separately or protect their activities in all places jointly. The former one cannot protect trajectories that traverse multiple places; while the latter ignores the differences among places and suffers the degradation of data utility (i.e., data accuracy). In this paper, we propose a w , n -differential privacy to protect any spatial-temporal sequence occurring in w successive timestamps and n -range places. To achieve better data utility, we propose two implementation algorithms, named Spatial-Temporal Budget Distribution (STBD) and Spatial-Temporal RescueDP (STR). Theoretical analysis and experimental results show that these two algorithms can achieve a balance between data utility and trajectory privacy guarantee.

show abstract

“…Among the existing research, Gaussian mechanism (GM) which draws noises from Gaussian distribution, combing with MA [11] which provides a tight estimates of privacy loss, has been widely applied in various SGD based machine learning tasks [5], [11], [12], [17]- [19]. Besides, considerable research has been conducted to improve the tradeoff from other perspectives, which can be categorized as sensitivity calibration [19], [20] that aims to improve the utility by adaptively calibrate the sensitivity, dimension reduction [21] and transformations [22] that aim to reduce the sensitivity in the lower-dimension or the transformed space instead of the original space, correlation exploration [23], [24] that aims to introduce fewer noises according to the correlation between gradients and target parameters, post-processing that applies denoising technique on the noisy gradient to improve the trained model utility [25]. However, these strategies are usually problem dependent.…”

Section: Introductionmentioning

confidence: 99%

p-Power Exponential Mechanisms for Differentially Private Machine Learning

Ren

Zhao

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Differentially private stochastic gradient descent (DP-SGD) that perturbs the clipped gradients is a popular approach for private machine learning. Gaussian mechanism GM, combined with the moments accountant (MA), has demonstrated a much better privacy-utility tradeoff than using the advanced composition theorem. However, it is unclear whether the tradeoff can be further improved by other mechanisms with different noise distributions. To this end, we extend GM (p = 2) to the generalized p-power exponential mechanism (pEM with p > 0) family and show its privacy guarantee. Straightforwardly, we can enhance the privacy-utility tradeoff of GM by searching noise distribution in the wider mechanism space. To implement pEM in practice, we design an effective sampling method and extend MA to pEM for tightly estimating privacy loss. Besides, we formally prove the non-optimality of GM based on the variation method. Numerical experiments validate the properties of pEM and illustrate a comprehensive comparison between pEM and the other two state-of-the-art methods. Experimental results show that pEM is preferred when the noise variance is relatively small to the signal and the dimension is not too high.

show abstract

Achieving correlated differential privacy of big data publication

Cited by 24 publications

References 5 publications

Machine Learning Concepts for Correlated Big Data Privacy

Machine Learning Concepts for Correlated Big Data Privacy

Differentially Private Web Browsing Trajectory over Infinite Streams

p-Power Exponential Mechanisms for Differentially Private Machine Learning

Contact Info

Product

Resources

About