Visible to the public Learning Light-Weight Edge-Deployable Privacy Models

TitleLearning Light-Weight Edge-Deployable Privacy Models
Publication TypeConference Paper
Year of Publication2018
AuthorsLim, Yeon-sup, Srivatsa, Mudhakar, Chakraborty, Supriyo, Taylor, Ian
Conference Name2018 IEEE International Conference on Big Data (Big Data)
Keywordsanonymization framework, anonymized data, Computational modeling, Data models, data privacy, data schema, data-driven applications, deployable models, Entropy, Internet, Internet-of-Things devices, Lattices, light-weight data anonymization, light-weight edge-deployable privacy models, Measurement, Metrics, model learning, nonPC devices, privacy, privacy models and measurement, pubcrawl, sequential anonymization approach
AbstractPrivacy becomes one of the important issues in data-driven applications. The advent of non-PC devices such as Internet-of-Things (IoT) devices for data-driven applications leads to needs for light-weight data anonymization. In this paper, we develop an anonymization framework that expedites model learning in parallel and generates deployable models for devices with low computing capability. We evaluate our framework with various settings such as different data schema and characteristics. Our results exhibit that our framework learns anonymization models up to 16 times faster than a sequential anonymization approach and that it preserves enough information in anonymized data for data-driven applications.
DOI10.1109/BigData.2018.8622410
Citation Keylim_learning_2018