Private and Continual Release of Statistics

Chan, T.-H. Hubert; Shi, Elaine; Song, Dawn

doi:10.1145/2043621.2043626

Cited by 310 publications

(444 citation statements)

References 23 publications

(25 reference statements)

Supporting

Mentioning

442

Contrasting

Order By: Relevance

“…In fact, the continual counting mechanism for bit streams by Chan et al [4] follows this design paradigm, where an object corresponds to a counter recording the number of 1's appearing in some time interval. However, not all objects can be readily privatized.…”

Section: Results and Contributionsmentioning

confidence: 99%

“…The idea of introducing randomness to perturb the outputs of algorithms allows a clean and formal way to analyze the tradeoff between preserving input privacy and achieving output accuracy. Recently, privacy has been studied in the continual setting [4,8,9]. Specifically, a change in the input in the current time step would not only affect the output in the current time step, but also might have a long lasting effect in the future.…”

Section: Related Workmentioning

confidence: 99%

“…Useful continual differentially private algorithms would need to mask this long term effect without sacrificing too much on accuracy. Chan et al [4] gave a differentially private mechanism to continually report the number of 1's seen so far in a bit stream with additive error that is polylogarithmic in the number of time steps. In the streaming model, Dwork et al [9] also distinguish between event-level privacy and user-level privacy: event-level privacy hides the occurrence of a particular event, while user-level privacy prevents adversaries from determining whether the stream contains any of a particular user's activities at all.…”

Section: Related Workmentioning

confidence: 99%

“…Note that a similar binary tree technique was also used in [1,4]. We now give a formal description of the PCC algorithm, as well as its theoretic guarantees.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Differentially Private Continual Monitoring of Heavy Hitters from Distributed Streams

Chan

Shi

et al. 2012

Privacy Enhancing Technologies

Self Cite

View full text Add to dashboard Cite

Abstract. We consider applications scenarios where an untrusted aggregator wishes to continually monitor the heavy-hitters across a set of distributed streams. Since each stream can contain sensitive data, such as the purchase history of customers, we wish to guarantee the privacy of each stream, while allowing the untrusted aggregator to accurately detect the heavy hitters and their approximate frequencies. Our protocols are scalable in settings where the volume of streaming data is large, since we guarantee low memory usage and processing overhead by each data source, and low communication overhead between the data sources and the aggregator.

show abstract

Section: Results and Contributionsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

“…Note that a similar binary tree technique was also used in [1,4]. We now give a formal description of the PCC algorithm, as well as its theoretic guarantees.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Differentially Private Continual Monitoring of Heavy Hitters from Distributed Streams

Chan

Shi

et al. 2012

Privacy Enhancing Technologies

Self Cite

View full text Add to dashboard Cite

show abstract

“…The algorithm can be interpreted as a post-optimization technique to the standard solution, by merging adjacent noisy counts. Intuitively, averaging over the neighboring noisy counts is able to eliminate the impact of zero-mean Laplace noise, based on the large number theorem [12].…”

Section: Noisefirstmentioning

confidence: 99%

Differentially Private Histogram Publication

Zhang

Xiao

et al. 2012

2012 IEEE 28th International Conference on Data Engineering

102

View full text Add to dashboard Cite

Abstract-Differential privacy (DP) is a promising scheme for releasing the results of statistical queries on sensitive data, with strong privacy guarantees against adversaries with arbitrary background knowledge. Existing studies on DP mostly focus on simple aggregations such as counts. This paper investigates the publication of DP-compliant histograms, which is an important analytical tool for showing the distribution of a random variable, e.g., hospital bill size for certain patients. Compared to simple aggregations whose results are purely numerical, a histogram query is inherently more complex, since it must also determine its structure, i.e., the ranges of the bins. As we demonstrate in the paper, a DP-compliant histogram with finer bins may actually lead to significantly lower accuracy than a coarser one, since the former requires stronger perturbations in order to satisfy DP. Moreover, the histogram structure itself may reveal sensitive information, which further complicates the problem.Motivated by this, we propose two novel algorithms, namely NoiseFirst and StructureFirst, for computing DP-compliant histograms. Their main difference lies in the relative order of the noise injection and the histogram structure computation steps. NoiseFirst has the additional benefit that it can improve the accuracy of an already published DP-complaint histogram computed using a naïve method. Going one step further, we extend both solutions to answer arbitrary range queries. Extensive experiments, using several real data sets, confirm that the proposed methods output highly accurate query answers, and consistently outperform existing competitors.

show abstract

A Machine Learning Approach for the Identification of Protein Secondary Structure Elements from Electron Cryo‐Microscopy Density Maps

Nasr

et al. 2012

Biopolymers

View full text Add to dashboard Cite

The accuracy of the secondary structure element (SSE) identification from volumetric protein density maps is critical for de‐novo backbone structure derivation in electron cryo‐microscopy (cryoEM). It is still challenging to detect the SSE automatically and accurately from the density maps at medium resolutions (∼5–10 Å). We present a machine learning approach, SSELearner, to automatically identify helices and β‐sheets by using the knowledge from existing volumetric maps in the Electron Microscopy Data Bank. We tested our approach using 10 simulated density maps. The averaged specificity and sensitivity for the helix detection are 94.9% and 95.8%, respectively, and those for the β‐sheet detection are 86.7% and 96.4%, respectively. We have developed a secondary structure annotator, SSID, to predict the helices and β‐strands from the backbone Cα trace. With the help of SSID, we tested our SSELearner using 13 experimentally derived cryo‐EM density maps. The machine learning approach shows the specificity and sensitivity of 91.8% and 74.5%, respectively, for the helix detection and 85.2% and 86.5% respectively for the β‐sheet detection in cryoEM maps of Electron Microscopy Data Bank. The reduced detection accuracy reveals the challenges in SSE detection when the cryoEM maps are used instead of the simulated maps. Our results suggest that it is effective to use one cryoEM map for learning to detect the SSE in another cryoEM map of similar quality. © 2012 Wiley Periodicals, Inc. Biopolymers 97: 698–708, 2012.

show abstract

Private and Continual Release of Statistics

Cited by 310 publications

References 23 publications

Differentially Private Continual Monitoring of Heavy Hitters from Distributed Streams

Differentially Private Continual Monitoring of Heavy Hitters from Distributed Streams

Differentially Private Histogram Publication

A Machine Learning Approach for the Identification of Protein Secondary Structure Elements from Electron Cryo‐Microscopy Density Maps

Contact Info

Product

Resources

About