Adversarial machine learning

Adversarial machine learning is the study of the attacks on <a href="/facts/Machine_learning/e0w0XJTu">machine learning</a> algorithms, and of the defenses against such attacks. A survey from May 2020 revealed practitioners' common feeling for better protection of machine learning systems in industrial applications.
Machine learning techniques are mostly designed to work on specific problem sets, under the assumption that the training and test data are generated from the same statistical distribution (<a href="/facts/Independent_and_identically_distributed_random_variables/othIRaWt">IID</a>). However, this assumption is often dangerously violated in practical high-stake applications, where users may intentionally supply fabricated data that violates the statistical assumption.
Most common attacks in adversarial machine learning include <a href="/facts/Evasion_attack/4An4fgUc">evasion attacks</a>, <a href="/facts/Data_poisoning_attack/4An4fgUc">data poisoning attacks</a>, <a href="/facts/Byzantine_attack/hucMXMBV">Byzantine attacks</a> and model extraction.

Adversarial machine learning open-in-new

Adversarial machine learning