Chromatic and spatial analysis of one-pixel attacks against an image classifier

by   Janne Alatalo, et al.

One-pixel attack is a curious way of deceiving neural network classifier by changing only one pixel in the input image. The full potential and boundaries of this attack method are not yet fully understood. In this research, the successful and unsuccessful attacks are studied in more detail to illustrate the working mechanisms of a one-pixel attack. The data comes from our earlier studies where we applied the attack against medical imaging. We used a real breast cancer tissue dataset and a real classifier as the attack target. This research presents ways to analyze chromatic and spatial distributions of one-pixel attacks. In addition, we present one-pixel attack confidence maps to illustrate the behavior of the target classifier. We show that the more effective attacks change the color of the pixel more, and that the successful attacks are situated at the center of the images. This kind of analysis is not only useful for understanding the behavior of the attack but also the qualities of the classifying neural network.


page 7

page 8

page 9


One-Pixel Attack Deceives Automatic Detection of Breast Cancer

In this article we demonstrate that a state-of-the-art machine learning ...

Deep adversarial attack on target detection systems

Target detection systems identify targets by localizing their coordinate...

Adversarial Attacks on Convolutional Neural Networks in Facial Recognition Domain

Numerous recent studies have demonstrated how Deep Neural Network (DNN) ...

Explainability Matters: Backdoor Attacks on Medical Imaging

Deep neural networks have been shown to be vulnerable to backdoor attack...

Joint Adversarial Training: Incorporating both Spatial and Pixel Attacks

Conventional adversarial training methods using attacks that manipulate ...

De-anonymization Attacks on Neuroimaging Datasets

Advances in imaging technologies, combined with inexpensive storage, hav...

Model-Targeted Poisoning Attacks: Provable Convergence and Certified Bounds

Machine learning systems that rely on training data collected from untru...