Fetching the paper…
Reading the bibliography…
We implement training of neural networks in secure multi-party computation (MPC) using quantization commonly used in said setting.
Applications of division by convergence
Goldschmidt, R. E · 1964
Earlier work this paper cites.
Computer approximations
Hart, J. F · 1978
Earlier work this paper cites.
Generalized secret sharing and monotone functions
Benaloh, J. C. and Leichter, J · 1990
Earlier work this paper cites.
Efficient multiparty protocols using circuit randomization
Beaver, D · 1992
Earlier work this paper cites.
Gradient-based learning applied to document recognition
LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P · 1998
Earlier work this paper cites.
Multiparty computation from threshold homomorphic encryption
Cramer, R., Damgrd, I., and Nielsen, J. B · 2001
Earlier work this paper cites.
A privacy-preserving protocol for neural-network-based computation
Barni, M., Orlandi, C., and Piva, A · 2006
Earlier work this paper cites.
Unconditionally secure constant-rounds multi-party computation for equality, comparison, bits and exponentiation
Damgrd, I., Fitzi, M., Kiltz, E., Nielsen, J. B., and Toft, T · 2006
Earlier work this paper cites.
Secure computation with fixed-point numbers
Catrina, O. and Saxena, A · 2010
Earlier work this paper cites.
Understanding the difficulty of training deep feedforward neural networks
Glorot, X. and Bengio, Y · 2010
Earlier work this paper cites.
MNIST handwritten digit database
LeCun, Y., Cortes, C., and Burges, C · 2010
Earlier work this paper cites.
Rectified linear units improve Restricted Boltzmann machines
Nair, V. and Hinton, G. E · 2010
Earlier work this paper cites.
Multiparty computation from somewhat homomorphic encryption
Damgrd, I., Pastro, V., Smart, N. P., and Zakarias, S · 2012
Earlier work this paper cites.
Secure computation on floating point numbers
Aliasgari, M., Blanton, M., Zhang, Y., and Steele, A · 2013
Earlier work this paper cites.
A systematic approach to practically efficient general two-party secure function evaluation protocols and their modular design
Kolesnikov, V., Sadeghi, A.-R., and Schneider, T · 2013
Earlier work this paper cites.
Algorithms in HElib
Halevi, S. and Shoup, V · 2014
Earlier work this paper cites.
Dropout: A simple way to prevent neural networks from overfitting
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R · 2014
Earlier work this paper cites.
Fast, privacy preserving linear regression over distributed datasets based on pre-distributed data
Cock, M. d., Dowsley, R., Nascimento, A. C., and Newman, S. C · 2015
Earlier work this paper cites.
ABY - A framework for efficient mixed-protocol secure two-party computation
Demmler, D., Schneider, T., and Zohner, M · 2015
Earlier work this paper cites.
Batch normalization: Accelerating deep network training by reducing internal covariate shift
Ioffe, S. and Szegedy, C · 2015
Earlier work this paper cites.
Adam: A method for stochastic optimization
Kingma, D. P. and Ba, J · 2015
Cited alongside, same era.
High-throughput semi-honest secure three-party computation with an honest majority
Araki, T., Furukawa, J., Lindell, Y., Nof, A., and Ohara, K · 2016
Cited alongside, same era.
Binarized neural networks
Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., and Bengio, Y · 2016
Cited alongside, same era.
Fixed point quantization of deep convolutional networks
Lin, D., Talathi, S., and Annapureddy, S · 2016
Cited alongside, same era.
Imagenet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., and Hinton, G. E · 2017
Cited alongside, same era.
Training quantized nets: A deeper understanding
Li, H., De, S., Xu, Z., Studer, C., Samet, H., and Goldstein, T · 2017
Cited alongside, same era.
New primitives for actively-secure MPC over rings with applications to private machine learning
Damgård, I., Escudero, D., Frederiksen, T. K., Keller, M., Scholl, P., and Volgushev, N · 2019
Later among the works it cites.
MArBled circuits: Mixing arithmetic and Boolean circuits with active security
Rotaru, D. and Wood, T · 2019
Later among the works it cites.
SecureNN: 3-party secure computation for neural network training
Wagh, S., Gupta, D., and Chandran, N · 2019
Later among the works it cites.
Secure evaluation of quantized neural networks
Dalskov, A. P. K., Escudero, D., and Keller, M · 2020
Later among the works it cites.
Use your brain! Arithmetic 3PC for any modulus with active security
Eerikson, H., Keller, M., Orlandi, C., Pullonen, P., Puura, J., and Simkin, M · 2020
Later among the works it cites.
Improved primitives for MPC over mixed arithmetic-binary circuits
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Oblivious neural network predictions via MiniONN transformations
Liu, J., Juuti, M., Lu, Y., and Asokan, N · 2017
Cited alongside, same era.
SecureML: A system for scalable privacy-preserving machine learning
Mohassel, P. and Zhang, Y · 2017
Cited alongside, same era.
Generalizing the SPDZ compiler for other protocols
Araki, T., Barak, A., Furukawa, J., Keller, M., Lindell, Y., Ohara, K., and Tsuchida, H · 2018
Cited alongside, same era.
Private machine learning in TensorFlow using secure computation
Dahl, M., Mancuso, J., Dupis, Y., Decoste, B., Giraud, M., Livingstone, I., Patriquin, J., and Uhma, G · 2018
Cited alongside, same era.
GAZELLE: A low latency framework for secure neural network inference
Juvekar, C., Vaikuntanathan, V., and Chandrakasan, A · 2018
Cited alongside, same era.
Overdrive: Making SPDZ great again
Keller, M., Pastro, V., and Rotaru, D · 2018
Cited alongside, same era.
Escudero, D., Ghosh, S., Keller, M., Rachuri, R., and Scholl, P · 2020
Later among the works it cites.
MP-SPDZ: A versatile framework for multi-party computation
Keller, M · 2020
Later among the works it cites.
Effectiveness of MPC-friendly softmax replacement
Keller, M. and Sun, K · 2020
Later among the works it cites.
Glyph: Fast and accurately training deep neural networks on encrypted data
Lou, Q., Feng, B., Fox, G. C., and Jiang, L · 2020
Later among the works it cites.
Faster secure multiparty computation of adaptive gradient descent
Lu, W.-j., Fang, Y., Huang, Z., Hong, C., Chen, C., Qu, H., Zhou, Y., and Ren, K · 2020
Later among the works it cites.
Delphi: A cryptographic inference service for neural networks
Mishra, P., Lehmkuhl, R., Srinivasan, A., Zheng, W., and Popa, R. A · 2020
Later among the works it cites.
CrypTFlow2: Practical 2-party secure inference
Rathee, D., Rathee, M., Kumar, N., Chandran, N., Gupta, D., Rastogi, A., and Sharma, R · 2020
Later among the works it cites.
Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms
Xiao, H., Rasul, K., and Vollgraf, R · 2020
Later among the works it cites.
Fantastic four: Honest-majority four-party secure computation with malicious security
Dalskov, A., Escudero, D., and Keller, M · 2021
Closest in time.
ATLAS: Efficient and scalable MPC in the honest majority setting
Goyal, V., Li, H., Ostrovsky, R., Polychroniadou, A., and Song, Y · 2021
Closest in time.
CrypTen: Secure multi-party computation meets machine learning
Knott, B., Venkataraman, S., Hannun, A., Sengupta, S., Ibrahim, M., and van der Maaten, L · 2021
Closest in time.
secureTF: A secure TensorFlow framework
Quoc, D. L., Gregor, F., Arnautov, S., Kunkel, R., Bhatotia, P., and Fetzer, C · 2021
Closest in time.
CryptGPU: Fast privacy-preserving machine learning on the GPU
Tan, S., Knott, B., Tian, Y., and Wu, D. J · 2021
Closest in time.
Falcon: Honest-majority maliciously secure framework for private deep learning
Wagh, S., Tople, S., Benhamouda, F., Kushilevitz, E., Mittal, P., and Rabin, T · 2021
Closest in time.