I Wagner, D Eckhoff - ACM Computing Surveys (Csur), 2018 - dl.acm.org
The goal of privacy metrics is to measure the degree of privacy enjoyed by users in a system and the amount of protection offered by privacy-enhancing technologies. In this way, privacy …
The large-scale monitoring of computer users' software activities has become commonplace, eg, for application telemetry, error reporting, or demographic profiling. This paper describes …
Differential privacy comes equipped with multiple analytical tools for the design of private data analyses. One important tool is the so-called" privacy amplification by subsampling" …
Deep learning techniques based on neural networks have shown significant success in a wide range of AI tasks. Large-scale training datasets are one of the critical factors for their …
Deep learning models are often trained on datasets that contain sensitive information such as individuals' shopping transactions, personal contacts, and medical records. An …
Local differential privacy (LDP), where users randomly perturb their inputs to provide plausible deniability of their data without the need for a trusted party, has been adopted …
D Eckhoff, I Wagner - IEEE Communications Surveys & …, 2017 - ieeexplore.ieee.org
Many modern cities strive to integrate information technology into every aspect of city life to create so-called smart cities. Smart cities rely on a large number of application areas and …
The wide-spread availability of rich data has fueled the growth of machine learning applications in numerous domains. However, growth in domains with highly-sensitive data …
Z Cai, X Zheng, J Wang, Z He - IEEE Transactions on Mobile …, 2022 - ieeexplore.ieee.org
The data collected in Internet of Thing (IoT) systems (IoT data) have stimulated dramatic extension to the boundary of commercialized data statistic analysis, owing to the pervasive …