logo Idiap Research Institute        
 [BibTeX] [Marc21]
Deep Variational Privacy Funnel: General Modeling with Applications in Face Recognition
Type of publication: Conference paper
Citation: Razeghi_ICASSP2024_2024
Publication status: Published
Booktitle: 49th IEEE International Conference on Acoustics, Speech and Signal Processing
Year: 2024
Month: April
Publisher: IEEE
URL: https://ieeexplore.ieee.org/do...
DOI: https://doi.org/10.1109/ICASSP48485.2024.10446646
Abstract: In this study, we harness the information-theoretic Privacy Funnel (PF) model to develop a method for privacy-preserving representation learning using an end-to-end training framework. We rigorously address the trade-off between obfuscation and utility. Both are quantified through the logarithmic loss, a measure also recognized as self-information loss. This exploration deepens the interplay between information-theoretic privacy and representation learning, offering substantive insights into data protection mechanisms for both discriminative and generative models. Importantly, we apply our model to state-of-the-art face recognition systems. The model demonstrates adaptability across diverse inputs, from raw facial images to both derived or refined embeddings, and is competent in tasks such as classification, reconstruction, and generation.
Keywords:
Projects Idiap
Biometrics Center
SAFER
Authors Razeghi, Behrooz
Rahimi, Parsa
Marcel, S├ębastien
Added by: [UNK]
Total mark: 0
Attachments
  • Razeghi_ICASSP2024_2024.pdf
Notes