Data Confidentiality in a Data Fusion Network

This lab project is a practical course, which can be taken as Digital Engineering project, but also students from other studies are welcome.

Intended Participants	Master Students
Instructors	Marko Ristic
SWS	2
Credits	6
Languages	English
Required Knowledge	Skilled Programming in Python Basic understanding of the Kalman filter
Desired Knowledge	Basic understanding of encryption comfortable using *nix terminal

Project Description

General description

Distributed state estimation and localization methods have become increasingly prevalent in modern networked tracking systems. Traditional distributed sensor localization methods involve the leakage of individual sensor or state information during estimation, and thus present a security concern. For example, a vehicle may be tracked by multiple sensors that different parties operate. If combining measurements is performed centrally, a trust is implied between participants. Sensor data, sensing modalities, sensor positions and hardware details could all be leaked to untrusted participants. To preserve the privacy of individual participants, this project focuses on the implementation of a cryptographically secure localization scheme.

The project consists of a small-scale camera network of Raspberry Pi nodes which can image and track a moving object. Imaging of the object is performed in advance, before measurements are forwarded centrally to a node and fused for a better estimate. The objective of the task is to understand and implement state-of-the-art encryption schemes which can be used to keep individual estimates confidential at the central node, revealing only the final fusion result. Students should aim to demonstrate the effectiveness of the encryption schemes in terms of accuracy and runtime.

Project goals

Implementation of state-of-the-art encryption schemes
Combining schemes with localization algorithm
Evaluation of implemented methods
Poster and report submission

Subtasks

Group task division and planning of project
Understanding of existing estimation and fusion algorithms used for localization
Modification of localization schemes to support encryption and decryption
Documentation of project

Registration

LSF

For any additional questions regarding the project or for any issues with registration, please email