.png){kind=icon}
.png){kind=icon}
Return
Federated Secure Computing
.png){kind=icon}
OA
AI
DOI：10.3390/informatics10040083.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Privacy-preserving computation (PPC) enables encrypted computation of private data. While advantageous in theory, the complex technology has steep barriers to entry in practice. Here, we derive design goals and principles for a middleware that encapsulates the demanding cryptography server side and provides a simple-to-use interface to client-side application developers. The resulting architecture, Federated Secure Computing, offloads computing-intensive tasks to the server and separates concerns of cryptography and business logic. It provides microservices through an Open API 3.0 definition and hosts multiple protocols through self-discovered plugins. It requires only minimal DevSecOps capabilities and is straightforward and secure. Finally, it is small enough to work in the internet of things (IoT) and in propaedeutic settings on consumer hardware. We provide benchmarks for calculations with a secure multiparty computation (SMPC) protocol, both for vertically and horizontally partitioned data. Runtimes are in the range of seconds on both dedicated workstations and IoT devices such as Raspberry Pi or smartphones. A reference implementation is available as free and open source software under the MIT license.
Keywords:
privacy-preserving computing
cloud computing
federated computing
cryptography
secure multiparty computation
propaedeutic framework
Python
free and open source software