Countering Adversarial Images Using Input Transformations

From statwiki
Revision as of 19:13, 14 November 2018 by Skoundin (talk | contribs)
Jump to navigation Jump to search

Motivation

As the use of machine intelligence has increased , robustness has become a critical feature to guarantee the reliability of deployed machine-learning systems. However, recent research has shown that existing models are not robust to small , adversarial designed perturbations of the input. Adversarial examples are inputs to Machine Learning models that an attacker has intentionally designed to cause the model to make a mistake.The adversarial examples are not specific to Images , but also Malware, Text Understanding ,Speech. Below example, a small perturbation when applied to original image, the prediction is changed.


Hence an urgent need for approaches that increase the robustness of learning systems to such examples