Manifold attack

09/13/2020
by   Khanh-Hung Tran, et al.
0

Machine Learning in general and Deep Learning in particular has gained much interest in the recent decade and has shown significant performance improvements for many Computer Vision or Natural Language Processing tasks. In order to deal with databases which have just a small amount of training samples or to deal with models which have large amount of parameters, the regularization is indispensable. In this paper, we enforce the manifold preservation (manifold learning) from the original data into latent presentation by using "manifold attack". The later is inspired in a fashion of adversarial learning : finding virtual points that distort mostly the manifold preservation then using these points as supplementary samples to train the model. We show that our approach of regularization provides improvements for the accuracy rate and for the robustness to adversarial examples.

READ FULL TEXT
research
09/13/2020

Semi-supervised dictionary learning with graph regularization and active points

Supervised Dictionary Learning has gained much interest in the recent de...
research
01/12/2022

Preventing Manifold Intrusion with Locality: Local Mixup

Mixup is a data-dependent regularization technique that consists in line...
research
06/13/2018

Manifold Mixup: Encouraging Meaningful On-Manifold Interpolation as a Regularizer

Deep networks often perform well on the data manifold on which they are ...
research
03/09/2020

Manifold Regularization for Adversarial Robustness

Manifold regularization is a technique that penalizes the complexity of ...
research
03/04/2021

Hard-label Manifolds: Unexpected Advantages of Query Efficiency for Finding On-manifold Adversarial Examples

Designing deep networks robust to adversarial examples remains an open p...
research
11/04/2018

Adversarial Gain

Adversarial examples can be defined as inputs to a model which induce a ...
research
02/11/2021

Quadric hypersurface intersection for manifold learning in feature space

The knowledge that data lies close to a particular submanifold of the am...

Please sign up or login with your details

Forgot password? Click here to reset