Adversarial machine learning

Topic | v1 | created by janarez |

Adversarial machine learning is a machine learning technique that attempts to fool models by supplying deceptive input. The most common reason is to cause a malfunction in a machine learning model. Most machine learning techniques were designed to work on specific problem sets in which the training and test data are generated from the same statistical distribution (IID). When those models are applied to the real world, adversaries may supply data that violates that statistical assumption. This data may be arranged to exploit specific vulnerabilities and compromise the results.


gives cons of Deep learning

Deep learning (also known as deep structured learning) is part of a broader family of machine learnin...

Edit details Edit relations Attach new author Attach new topic Attach new resource

discussed in Breaking Linear Classifiers on ImageNet

9.0 rating 2.0 level 10.0 clarity 7.0 background – 1 rating

You’ve probably heard that Convolutional Networks work very well in practice and across a wide range...

discussed in Explaining and Harnessing Adversarial Examples

Several machine learning models, including neural networks, consistently misclassify adversarial exam...