scholarly journals A Dual Privacy Preserving Algorithm in Spatial Crowdsourcing

2020 ◽  
Vol 2020 ◽  
pp. 1-6
Author(s):  
Shengxiang Wang ◽  
Xiaofan Jia ◽  
Qianqian Sang
Keyword(s):  
Waiting Time ◽  
Task Allocation ◽  
Privacy Protection ◽  
Privacy Preserving ◽  
Smart Devices ◽  
Location Information ◽  
Spatial Crowdsourcing ◽  
Allocation Efficiency ◽  
And Task

Spatial crowdsourcing assigns location-related tasks to a group of workers (people equipped with smart devices and willing to complete the tasks), who complete the tasks according to their scope of work. Since space crowdsourcing usually requires workers’ location information to be uploaded to the crowdsourcing server, it inevitably causes the privacy disclosure of workers. At the same time, it is difficult to allocate tasks effectively in space crowdsourcing. Therefore, in order to improve the task allocation efficiency of spatial crowdsourcing in the case of large task quantity and improve the degree of privacy protection for workers, a new algorithm is proposed in this paper, which can improve the efficiency of task allocation by disturbing the location of workers and task requesters through k-anonymity. Experiments show that the algorithm can improve the efficiency of task allocation effectively, reduce the task waiting time, improve the privacy of workers and task location, and improve the efficiency of space crowdsourcing service when facing a large quantity of tasks.

scholarly journals Adversarial Learning of Privacy-Preserving and Task-Oriented Representations

2020 ◽  
Vol 34 (07) ◽  
pp. 12434-12441
Author(s):  
Taihong Xiao ◽  
Yi-Hsuan Tsai ◽  
Kihyuk Sohn ◽  
Manmohan Chandraker ◽  
Ming-Hsuan Yang
Keyword(s):  
Machine Learning ◽  
Privacy Protection ◽  
Input Data ◽  
Service Providers ◽  
Privacy Preserving ◽  
Learning Systems ◽  
Model Inversion ◽  
Perceptual Distance ◽  
Task Oriented ◽  
And Task

Data privacy has emerged as an important issue as data-driven deep learning has been an essential component of modern machine learning systems. For instance, there could be a potential privacy risk of machine learning systems via the model inversion attack, whose goal is to reconstruct the input data from the latent representation of deep networks. Our work aims at learning a privacy-preserving and task-oriented representation to defend against such model inversion attacks. Specifically, we propose an adversarial reconstruction learning framework that prevents the latent representations decoded into original input data. By simulating the expected behavior of adversary, our framework is realized by minimizing the negative pixel reconstruction loss or the negative feature reconstruction (i.e., perceptual distance) loss. We validate the proposed method on face attribute prediction, showing that our method allows protecting visual privacy with a small decrease in utility performance. In addition, we show the utility-privacy trade-off with different choices of hyperparameter for negative perceptual distance loss at training, allowing service providers to determine the right level of privacy-protection with a certain utility performance. Moreover, we provide an extensive study with different selections of features, tasks, and the data to further analyze their influence on privacy protection.

scholarly journals Efficient task assignment in spatial crowdsourcing with worker and task privacy protection

2017 ◽  
Vol 22 (2) ◽  
pp. 335-362 ◽  
Author(s):  
An Liu ◽  
Weiqi Wang ◽  
Shuo Shang ◽  
Qing Li ◽  
Xiangliang Zhang
Keyword(s):  
Privacy Protection ◽  
Task Assignment ◽  
Spatial Crowdsourcing ◽  
And Task

Division of labor

2018 ◽  
Author(s):  
Phanish Puranam
Keyword(s):  
Division Of Labor ◽  
Task Allocation ◽  
Task Structure ◽  
Heuristic Approaches ◽  
Object Based ◽  
The Creation ◽  
Task Division ◽  
And Task

Division of labor involves task division and task allocation. An extremely important consequence of task division and allocation is the creation of interdependence between agents. In fact, division of labor can be seen as a process that converts interdependence between tasks into interdependence between agents. While there are many ways in which the task structure can be chunked and divided among agents, two important heuristic approaches involve division of labor by activity vs. object. I show that a choice between these two forms of division of labor only arises when the task structure is non-decomposable, but the product itself is decomposable. When the choice arises, a key criterion for selection between activity vs. object-based division of labor is the gain from specialization relative to the gain from customization.

scholarly journals Local Privacy-Preserving Dynamic Worker Locations in Spatial Crowdsourcing

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 27359-27373
Author(s):  
Feng Lin ◽  
Jianhao Wei ◽  
Junyi Li ◽  
Jianming Zhang ◽  
Bo Yin
Keyword(s):  
Privacy Preserving ◽  
Spatial Crowdsourcing
Sign in / Sign up

Export Citation Format

Share Document