IronM: Privacy-Preserving Reliability Estimation of Heterogeneous Data for Mobile Crowdsensing

Zhao, Bowen; Tang, Shaohua; Liu, Ximeng; Zhang, Xinglin; Chen, Wei-Neng

doi:10.1109/jiot.2020.2975546

Cited by 27 publications

(8 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RSI datasets are just one subset of a much broader phenomena of large dataset creation for deep learning applications in the scientific and commercial domains. They have be used in a variety of contexts, ranging from text-based genomic analysis [35] and natural language processing [36] to image-and videobased vision tasks for media scraped from the web [37] or captured from distributed sensors like smartphones and traffic cameras [38,39]. Given the sheer size and complexity of such multimodal, multidisciplinary data sources, it might be expected that models trained on these datasets contain finelydiscriminative, highly-diverse, and inclusive features suitable for any number of uses worldwide.…”

Section: A Current Challengesmentioning

confidence: 99%

Methods for Measuring Geodiversity in Large Overhead Imagery Datasets

Wesley

Matisziw

2021

IEEE Access

View full text Add to dashboard Cite

Geographic variation in the appearance of objects on Earth is readily observable in remotely sensed imagery (RSI) and somewhat intuitive to understand for most peoplemany classes of objects (houses, vehicles, crop fields etc.) simply look different depending on their location. This variation has recently been shown to have important implications when training machine learning models on geotagged image datasets for specific object detection and classification tasks. For example, models trained on datasets with ethnocentric biases in image content have been shown to misclassify objects in under-sampled regions, particularly in least-developed countries. The need to evaluate the growing corpus of RSI datasets for representativeness, heterogeneity and geodiversity is therefore high; yet scalable methods for measuring these concepts are absent in the remote sensing domain. This paper introduces the first dataset analysis methods for detecting and assessing geodiversity problems in large RSI datasets, based on geospatial adaptations of the Fréchet Inception Distance and Inception Score in the deep learning framework. Geospatial Fréchet Distance is proposed as a dissimilarity measure for image features of an object class across geographic regions useful for comparing differences in object class appearance in different locations and/or spatial scales. A complementary Geospatial Inception Score is proposed to quantify heterogeneity of geographic context present in dataset labels within particular regions/locations, taking into account the labels themselves as well as their immediate surroundings. Rigorous tests of these methods on simulated RSI datasets demonstrate their stability, sensitivity, and the broad range of dataset analyses to which they can be applied.INDEX TERMS Big geodata, deep convolutional neural networks, explainable ai, geographic domain shift, GIS-remote sensing fusion, imagery interpretation, spatial data analysis This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.

show abstract

Section: A Current Challengesmentioning

confidence: 99%

Methods for Measuring Geodiversity in Large Overhead Imagery Datasets

Wesley

Matisziw

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Some incentive mechanism methods only consider the cost of users to collect sensing data but do not consider the potential cost of privacy disclosure. Recently, some researchers have designed privacy-preserving incentive mechanisms [26][27][28]. In [20], an incentive method is proposed to protect the user's identity and data privacy.…”

Section: Introductionmentioning

confidence: 99%

Privacy-Preserving Incentive Mechanism for Mobile Crowdsensing

Wan

Yue

Liao

2021

Security and Communication Networks

View full text Add to dashboard Cite

Incentive mechanisms are crucial for motivating adequate users to provide reliable data in mobile crowdsensing (MCS) systems. However, the privacy leakage of most existing incentive mechanisms leads to users unwilling to participate in sensing tasks. In this paper, we propose a privacy-preserving incentive mechanism based on truth discovery. Specifically, we use the secure truth discovery scheme to calculate ground truth and the weight of users’ data while protecting their privacy. Besides, to ensure the accuracy of the MCS results, a data eligibility assessment protocol is proposed to remove the sensing data of unreliable users before performing the truth discovery scheme. Finally, we distribute rewards to users based on their data quality. The analysis shows that our model can protect users’ privacy and prevent the malicious behavior of users and task publishers. In addition, the experimental results demonstrate that our model has high performance, reasonable reward distribution, and robustness to users dropping out.

show abstract

“…To widely collect sensory data and construct efficient MCS applications, multidimensional sensory data are often aggregated in the cloud platform. For example, larger scale urban MCS applications usually need to analyze the multidimensional sensory data to generate multiple urban sensors maps 12,13 . A task requester needs to aggregate the statistics of temperature, humidity, and noise at specific locations.…”

Section: Introductionmentioning

confidence: 99%

A verifiable and privacy‐preserving multidimensional data aggregation scheme in mobile crowdsensing

Jiang

Zhao

Tang

et al. 2020

Trans Emerging Tel Tech

Self Cite

View full text Add to dashboard Cite

Mobile crowdsensing has become a popular data collection paradigm and has been extensively studied. Since the analysis of sensory data usually reveals privacy of mobile users, data aggregation technology is widely used to avoid privacy disclosure. However, traditional privacy‐preserving data aggregation schemes cannot provide aggregate statistics of multidimensional data in fine‐grained areas or resist collusive attacks. Moreover, the cloud platform is not fully trusted, and it is challenging to verify the correctness of data aggregation results. To provide privacy‐preserving multidimensional statistics within fine‐grained areas and verify results of data aggregation, we propose a verifiable privacy‐preserving data aggregation scheme in this article, which is based on data double‐masking, Shamir's secret sharing, and bilinear mapping. Specifically, a key agreement is utilized to establish mask seeds for users, while the users are required to extend mask values and generate the verification key with bilinear mapping. The cloud platform aggregates masked data and provides proof of computational results. Theoretical analysis demonstrates our scheme can protect data and location privacy, verify the aggregation results, and improve the rubustness to failure. The simulation results show that the computational overhead of mobile devices by using the proposed anticollusion scheme is better than that of homomorphic encryption. In addition, the computational complexity of task requesters is less than that of the PVPA scheme for verification of multidimensional aggregation results.

show abstract

IronM: Privacy-Preserving Reliability Estimation of Heterogeneous Data for Mobile Crowdsensing

Cited by 27 publications

References 47 publications

Methods for Measuring Geodiversity in Large Overhead Imagery Datasets

Methods for Measuring Geodiversity in Large Overhead Imagery Datasets

Privacy-Preserving Incentive Mechanism for Mobile Crowdsensing

A verifiable and privacy‐preserving multidimensional data aggregation scheme in mobile crowdsensing

Contact Info

Product

Resources

About