Seminar: Encryption of audio data for context recognition
Background:
The increased use of audio data coming from microphones in ubiquitous systems offers new possibilites for context recognition, but causes severe privacy concerns at the same time. This problem is particularly relevant in digital health contexts, as privacy is a top priority in medical data. The goal of this seminar is to give students an overview of signal properties in audio signal which could be crucial for data protection. Afterwards, students research current literature to get an overview of state-of-the-art architectures in the field of audio encryption. Furthermore, students record exemplary audio data and visualise different artifacts. From data investigation, the participants develop a signal processing pipeline that separates relevant health context information from privacy threatening components, such as speech.
Aim:
Develop cryptographic signal processing pipelines for audio data encryption.
Learning Objectives:
- Understand privacy threats caused by the usage of audio data
- Understand signal properties that can be exploited for audio privacy protection
- Develop signal processing pipelines for audio data protection
Data
Project type | Seminar |
ECTS | 2.5, 5, 7.5 |
Language | English and/or German |
Period | Summer term 2021 |
Presence time | Virtual seminar, working from remote |
Useful knowledge | Signal processing, especially audio, cryptography |
Work distribution | Literature research, data investigation and visualisation, algorithm development |
Med. Eng. designation | Advanced Context Recognition (ACR) |
StudOn link | Link will follow shortly. |
First meeting | Online introduction/Vorbesprechung |
Registration | Via StudOn, obligatory after introduction. |
Literature
Up-to-date literature recommendations are provided during the meetings.
Examination
Final presentation and final report.
Contact
David Kopyto
- Job title: Researcher
- Address:
Henkestraße 91, Haus 7, 1. OG
91052 Erlangen
Germany - Phone number: +49 9131 85-23608
- Email: david.kopyto@fau.de