Cloud-Assisted IoT Systems Privacy--2018Q4
PI(s), Co-PI(s), Researchers: Fengjun Li, Bo Luo
HARD PROBLEM(S) ADDRESSED
The goal of this project is to develop principles and methods to model privacy needs, threats, and protection mechanisms in cloud-assisted IoT systems. The work aims to address the hard problems of resilient architectures, security metrics as well as scalability and composability.
PUBLICATIONS
N/A
PUBLIC ACCOMPLISHMENT HIGHLIGHTS
- Designed a privacy-preserving protocol for model training, as an extended scheme to support our privacy-preserving classification protocol.
In the cloud-assisted IoT scenario, IoT devices are continuously generating new data. When new data becomes available, the incremental learning scheme can integrate the new data into the quadratic program and modify the kernel and regularization parameters if necessary. This online, active and incremental batch learning capability is critical to cloud-assisted IoT application scenarios.
COMMUNITY ENGAGEMENTS
- Fengjun Li, invited talk on "Cloud-Assisted Privacy-Preserving Classification for IoT Applications," in the 2019 NSA SoS Lablet Quarterly Meeting, Berkeley, CA, January 10, 2019.
EDUCATIONAL ADVANCES
N/A