mlsanityData to 14 Oct 2026

Photonic Differential Privacy with Direct Feedback Alignment

arXiv 2106.03645 ↗First posted 7 Jun 2021cs.LG cs.CRcited by 5

Not on the map. Why?

Abstract (arXiv)

Optical Processing Units (OPUs) -- low-power photonic chips dedicated to large scale random projections -- have been used in previous work to train deep neural networks using Direct Feedback Alignment (DFA), an effective alternative to backpropagation. Here, we demonstrate how to leverage the intrinsic noise of optical random projections to build a differentially private DFA mechanism, making OPUs a solution of choice to provide a private-by-design training. We provide a theoretical analysis of our adaptive privacy mechanism, carefully measuring how the noise of optical random projections propagates in the process and gives rise to provable Differential Privacy. Finally, we conduct experiments demonstrating the ability of our learning procedure to achieve solid end-task performance.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 20 of its 35 references that are in the map. First posted on arXiv 7 Jun 2021.

Builds on

20 of 35 references.

References · 20

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  2. 2016Deep Learning with Differential Privacycited by 2,728
  3. 2017Renyi Differential Privacycited by 650
  4. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  5. 2018Scalable Private Learning with PATEcited by 269
  6. 2016Direct Feedback Alignment Provides Learning in Deep Neural Networkscited by 240
  7. 2018Subsampled R'enyi Differential Privacy and Analytical Moments Accountantcited by 236
  8. 2018Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoisingcited by 218
  9. 2020Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architecturescited by 56
  10. 2018Training of photonic neural networks through in situ backpropagationcited by 45
  11. 2017Differentially Private Mixture of Generative Neural Networkscited by 39
  12. 2020Three Variants of Differential Privacy: Lossless Conversion and Applicationscited by 26
8 more
  1. 2014High-level numerical simulations of noise in CCD and CMOS photosensors: review and tutorialcited by 23
  2. 2017Towards Practical Differential Privacy for SQL Queriescited by 19
  3. 2020Removing Disparate Impact of Differentially Private Stochastic Gradient Descent on Model Accuracycited by 13
  4. 2020Hardware Beyond Backpropagation: a Photonic Co-Processor for Direct Feedback Alignmentcited by 10
  5. 2018MVG Mechanism: Differential Privacy under Matrix-Valued Querycited by 7
  6. 2020Differentially Private Deep Learning with Direct Feedback Alignmentcited by 7
  7. 2019Kernel computations from large-scale random features obtained by Optical Processing Unitscited by 6
  8. 2019Backpropagation through nonlinear units for all-optical training of neural networkscited by 2

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 2.

5 papers.

  1. 2023Nonlinear optical encoding enabled by recurrent linear scatteringcited by 15
  2. 2022Self-Supervised Pretraining for Differentially Private Learningcited by 4
  3. 2022Scaling Laws Beyond Backpropagationcited by 4
  4. 2024Streamlined optical training of large-scale modern deep learning architectures with direct feedback alignmentcited by 3
  5. 2024DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignmentcited by 2