no code implementations • 31 Mar 2023 • Homa Esfahanizadeh, Adam Yala, Rafael G. L. D'Oliveira, Andrea J. D. Jaba, Victor Quach, Ken R. Duffy, Tommi S. Jaakkola, Vinod Vaikuntanathan, Manya Ghobadi, Regina Barzilay, Muriel Médard
Allowing organizations to share their data for training of machine learning (ML) models without unintended information leakage is an open problem in practice.
no code implementations • 28 Jan 2022 • Adam Yala, Victor Quach, Homa Esfahanizadeh, Rafael G. L. D'Oliveira, Ken R. Duffy, Muriel Médard, Tommi S. Jaakkola, Regina Barzilay
We quantify privacy as the number of attacker guesses required to re-identify a single image (guesswork).
1 code implementation • 4 Jun 2021 • Adam Yala, Homa Esfahanizadeh, Rafael G. L. D' Oliveira, Ken R. Duffy, Manya Ghobadi, Tommi S. Jaakkola, Vinod Vaikuntanathan, Regina Barzilay, Muriel Medard
We propose to approximate this family of encoding functions through random deep neural networks.
no code implementations • 8 Jun 2020 • Alejandro Cohen, Amit Solomon, Ken R. Duffy, Muriel Médard
The estimate is recycled to reduce the Signal to Noise Ratio (SNR) of an orthogonal channel that is experiencing correlated noise and so improve the accuracy of its decoding.
Information Theory Information Theory
no code implementations • 9 Aug 2019 • Alexander S. Miles, Philip D. Hodgkin, Ken R. Duffy
An alternative possibility, supported by the data in Kinjo et al. (Nature Commun., 2015), is that memory precursors are created after the expansion phase, which is a deduction not possible from the mathematical methods provided in Buchholz et al. (Science, 2013).
no code implementations • 2 Oct 2017 • Hao Wang, Lisa Vo, Flavio P. Calmon, Muriel Médard, Ken R. Duffy, Mayank Varia
Here, an analyst is allowed to reconstruct (in a mean-squared error sense) certain functions of the data (utility), while other private functions should not be reconstructed with distortion below a certain threshold (privacy).