Fetching the paper…

Reading the bibliography…

2019

MimosaNet: An Unrobust Neural Network Preventing Model Stealing

Szentannai, Kálmán, Al-Afandi, Jalal, Horváth, András

Original
PDF
Post on X

Understand

Deep Neural Networks are robust to minor perturbations of the learned network parameters and their minor modifications do not change the overall network response significantly.

This allows space for model stealing, where a malevolent attacker can steal an already trained network, modify the weights and claim the new network his own intellectual property.
In certain cases this can prevent the free distribution and application of networks in the embedded domain.
In this paper, we propose a method for creating an equivalent version of an already trained fully connected deep neural network that can prevent network stealing: namely, it produces the same responses and classification accuracy, but it is extremely sensitive to weight changes.

MimosaNet: An Unrobust Neural Network Preventing Model Stealing · Around

Built on

E. Koch and J. Zhao, “Towards robust and hidden image copyright labeling,” in IEEE Workshop on Nonlinear Signal and Image Processing , vol. 1174. Neos Marmaras, Greece, 1995, pp. 185–206
1995
Earlier work this paper cites.
R. B. Wolfgang and E. J. Delp, “A watermark for digital images,” in Image Processing, 1996. Proceedings., International Conference on , vol. 3. IEEE, 1996, pp. 219–222
1996
Earlier work this paper cites.
Y. LeCun, C. Cortes, and C. Burges, “Mnist handwritten digit database,” AT&T Labs [Online]. Available: http://yann. lecun. com/exdb/mnist , vol. 2, 2010
2010
Earlier work this paper cites.
D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980 , 2014
Original
2014
Earlier work this paper cites.

Similar

G. Hinton, O. Vinyals, and J. Dean, “Distilling the knowledge in a neural network,” arXiv preprint arXiv:1503.02531 , 2015
Original
2015
Cited alongside, same era.
H. Zarrabi, M. Hajabdollahi, S. Soroushmehr, N. Karimi, S. Samavi, and K. Najarian, “Reversible image watermarking for health informatics systems using distortion compensation in wavelet domain,” arXiv preprint arXiv:1802.07786 , 2018
Original
2018
Cited alongside, same era.
H. Xu, Y. Su, Z. Zhao, Y. Zhou, M. R. Lyu, and I. King, “Deepobfuscation: Securing the structure of convolutional neural networks via knowledge distillation,” arXiv preprint arXiv:1806.10313 , 2018
Original
2018
Cited alongside, same era.

Then

L. Gomez, A. Ibarrondo, J. Márquez, and P. Duverger, “Intellectual property protection for distributed neural networks,” 2018
2018
Later among the works it cites.
D. Hitaj and L. V. Mancini, “Have you stolen my model? evasion attacks against deep neural network watermarking techniques,” arXiv preprint arXiv:1809.00615 , 2018
Original
2018
Later among the works it cites.
R. Namba and J. Sakuma, “Robust watermarking of neural network with exponential weighting,” arXiv preprint arXiv:1901.06151 , 2019
Original
2019
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…