Privacy-Preserving Speech and Audio Processing
Carnegie Mellon University –
The privacy of personal data has generally been considered inviolable. On the other hand, in nearly any interaction, whether it is with other people or with computerized systems, we reveal information about ourselves. Sometimes this is intended, for instance when we use a biometric system to authenticate ourselves, or when we explicitly provide personal information in some manner. Often, however, it is unintended; for instance a simple search performed on a server reveals information about our preferences. An interaction with a voice recognition system reveals information to the system about our gender, nationality (accent), and possibly emotional state and age.
Regardless of whether the exposure of information is intentional or not, it could be misused, potentially setting us at financial, social and even physical risk. These concerns about exposure of information has spawned a large and growing body of research, addressing various issues about how information may be leaked, and how to protect it.
One area of concern are sound data, particularly voice. For instance, voice-authentication systems and voice-recognition systems are becoming increasingly popular and commonplace. However, in the process of using these services, a user exposes himself to potential abuse: as mentioned above the server, or an eavesdropper, may obtain unintended demographic information about the user by analyzing the voice and sell this information. It may edit recordings to create fake recordings the user never spoke. Other such issues can be listed. Merely encrypting the data for transmission does not protect the user, since the recepient (the server) must finally have access to the data in the clear (i.e. decrypted form) in order to perform its processing.
In this talk, we will discuss solutions for privacy-preserving sound processing, which enable a user to employ sound- or voice-processing services without explosing themselves to risks such as the above.
We will describe the basics of privacy-preserving techniques for data processing, including homomorphic encryption, oblivious transfer, secret sharing, and secure-multiparty computation. We will describe how these can be employed to build secure “primitives” for computation, that enable users to perform basic steps of computation without revealing information. We will describe the privacy issues with respect to these operations. We will then briefly present schemes that employ these techniques for privacy-preserving signal processing and biometrics.
We will then delve into uses for sound, and particularly voice processing, including authentication, classification and recognition, and discuss computational and accuracy issues.
Finally we will present a newer class of methods based on exact matches built upon locality sensitive hashing and universal quantization, which enables several of the above privacy-preserving operations at a different operating point of privacy-accuracy tradeoff.
Date: 2012-Sep-28 Time: 14:00:00 Room: 020
For more information:
Workshop “Metabolism and mathematical models: Two for a tango” – 2nd Edition
Title: Workshop Metabolism and mathematical models: Two for a tango – 2nd Edition
Dates: October 25-26, 2022
Location: This workshop will be held in a virtual way
The topic of this workshop is metabolism in general, with a special focus, although not exclusive, on parasitology. Besides an exploration of the biological, biochemical and biomedical aspects, the workshop will also aim at presenting some of the mathematical modelling, algorithmic theory and software development that have become crucial to explore such aspects.
This workshop is being organised in the context of two projects, both with the Inria European Team Erable. One of the projects involves a partnership with the University of São Paulo (USP), in São Paulo, Brazil, more specifically the Institute of Mathematics and Statistics (IME) and the Institute of Biomedical Sciences – Inria Associated Team Capoeira – and the other involves the Inesc-ID/IST in Portugal, ETH in Zürich and EMBL in Heidelberg – H2020 Twinning Project Olissipo.
The workshop is open to all members of these two projects but also, importantly, to the community in general.
The program and more details are available here.