Fetching the paper…

Reading the bibliography…

2017

Dense Associative Memory is Robust to Adversarial Inputs

Krotov, Dmitry, Hopfield, John J

Original
PDF
Post on X

Understand

Deep neural networks (DNN) trained in a supervised way suffer from two known problems.

First, the minima of the objective function used in learning correspond to data points (also known as rubbish examples or fooling images) that lack semantic similarity with the training data.
Second, a clean input can be changed by a small, and often imperceptible for human vision, perturbation, so that the resulting deformed input is misclassified by the network.
These findings emphasize the differences between the ways DNN and humans classify patterns, and raise a question of designing learning algorithms that more accurately mimic human perception compared to the existing methods.

Dense Associative Memory is Robust to Adversarial Inputs · Around

Built on

Simard, P.Y., Steinkraus, D. and Platt, J.C., 2003, August. Best practices for convolutional neural networks applied to visual document analysis. In ICDAR (Vol. 3, pp. 958-962)
2003
Earlier work this paper cites.
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I. and Fergus, R., 2013. Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199
Original
2013
Earlier work this paper cites.
Gu, S. and Rigazio, L., 2014. Towards deep neural network architectures robust to adversarial examples. arXiv preprint arXiv:1412.5068
Original
2014
Earlier work this paper cites.
Goodfellow, I.J., Shlens, J. and Szegedy, C., 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572
Original
2014
Earlier work this paper cites.
Nguyen, A., Yosinski, J. and Clune, J., 2015, June. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 427-436). IEEE
2015
Earlier work this paper cites.

Similar

Miyato, T., Maeda, S.I., Koyama, M., Nakae, K. and Ishii, S., 2015. Distributional smoothing with virtual adversarial training. stat, 1050, p.25
2015
Cited alongside, same era.
Huang, R., Xu, B., Schuurmans, D. and Szepesvári, C., 2015. Learning with a strong adversary. CoRR, abs/1511.03034
Original
2015
Cited alongside, same era.
Nokland, A., 2015. Improving back-propagation by adding an adversarial gradient. arXiv preprint arXiv:1510.04189
Original
2015
Cited alongside, same era.
Papernot, N., McDaniel, P. and Goodfellow, I., 2016. Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples. arXiv preprint arXiv:1605.07277
Original
2016
Cited alongside, same era.

Then

Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Berkay Celik, Z. and Swami, A., 2016. Practical Black-Box Attacks against Deep Learning Systems using Adversarial Examples. arXiv preprint arXiv:1602.02697
Original
2016
Later among the works it cites.
Kurakin, A., Goodfellow, I. and Bengio, S., 2016. Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533
Original
2016
Later among the works it cites.
Wang, Q., Guo, W., Zhang, K., Xing, X., Giles, C.L. and Liu, X., 2016. Random Feature Nullification for Adversary Resistant Deep Architecture. arXiv preprint arXiv:1610.01239
Original
2016
Later among the works it cites.
Krotov, D. and Hopfield, J.J., 2016. Dense Associative Memory for Pattern Recognition. Advances in Neural Information Processing Systems 2016, in press, arXiv preprint arXiv:1606.01164
Original
2016
Later among the works it cites.

Beyond the bibliography

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

Open on alphaXiv

alphaXiv is searching for related work…