Next Article in Journal
Accessing Imbalance Learning Using Dynamic Selection Approach in Water Quality Anomaly Detection
Previous Article in Journal
A Novel Technique for Determination of Residual Direct-Current Voltage of Liquid Crystal Cells with Vertical and In-Plane Electric Fields
 
 
Article

On the Relationship between Generalization and Robustness to Adversarial Examples

VISILAB, University of Castilla La Mancha, ETSII, 13071 Ciudad Real, Spain
*
Author to whom correspondence should be addressed.
Academic Editor: Jan Awrejcewicz
Symmetry 2021, 13(5), 817; https://doi.org/10.3390/sym13050817
Received: 23 March 2021 / Revised: 9 April 2021 / Accepted: 30 April 2021 / Published: 7 May 2021
One of the most intriguing phenomenons related to deep learning is the so-called adversarial examples. These samples are visually equivalent to normal inputs, undetectable for humans, yet they cause the networks to output wrong results. The phenomenon can be framed as a symmetry/asymmetry problem, whereby inputs to a neural network with a similar/symmetric appearance to regular images, produce an opposite/asymmetric output. Some researchers are focused on developing methods for generating adversarial examples, while others propose defense methods. In parallel, there is a growing interest in characterizing the phenomenon, which is also the focus of this paper. From some well known datasets of common images, like CIFAR-10 and STL-10, a neural network architecture is first trained in a normal regime, where training and validation performances increase, reaching generalization. Additionally, the same architectures and datasets are trained in an overfitting regime, where there is a growing disparity in training and validation performances. The behaviour of these two regimes against adversarial examples is then compared. From the results, we observe greater robustness to adversarial examples in the overfitting regime. We explain this simultaneous loss of generalization and gain in robustness to adversarial examples as another manifestation of the well-known fitting-generalization trade-off. View Full-Text
Keywords: machine learning; computer vision; deep learning; adversarial examples; adversarial robustness; overfitting machine learning; computer vision; deep learning; adversarial examples; adversarial robustness; overfitting
Show Figures

Figure 1

MDPI and ACS Style

Pedraza, A.; Deniz, O.; Bueno, G. On the Relationship between Generalization and Robustness to Adversarial Examples. Symmetry 2021, 13, 817. https://doi.org/10.3390/sym13050817

AMA Style

Pedraza A, Deniz O, Bueno G. On the Relationship between Generalization and Robustness to Adversarial Examples. Symmetry. 2021; 13(5):817. https://doi.org/10.3390/sym13050817

Chicago/Turabian Style

Pedraza, Anibal, Oscar Deniz, and Gloria Bueno. 2021. "On the Relationship between Generalization and Robustness to Adversarial Examples" Symmetry 13, no. 5: 817. https://doi.org/10.3390/sym13050817

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop