Adversarial-Attacks
Nontargeted Adversarial Attacks
The goal of the non-targeted attack is to slightly modify source image in a way that image will be classified incorrectly by generally unknown machine learning classifier.
Targeted Adversarial Attacks
The goal of the targeted attack is to slightly modify source image in a way that image will be classified as specified target class by generally unknown machine learning classifier.
Defense Against Adversarial Attack
The goal of the defense is to build machine learning classifier which is robust to adversarial example, i.e. can classify adversarial images correctly.
References
EXPLORING THE SPACE OF BLACK-BOX ATTACKS ON DEEP NEURAL NETWORKS - pdf
Adversarial Examples: Attacks and Defenses for Deep Learning - pdf
Practical Black-Box Attacks against Machine Learning - pdf
Examples
