Adversarial Learning: A Critical Review and Active Learning Study
This work addresses adversarial learning challenges for machine learning practitioners, but it appears incremental as it builds on existing methods with a new strategy.
The paper first critically reviews prior adversarial learning works, identifying significant limitations, and then experimentally studies adversarial active learning, investigating a mixed sample selection strategy to combat adversarial disruption of classifier learning.
This papers consists of two parts. The first is a critical review of prior art on adversarial learning, identifying some significant limitations of previous works. The second part is an experimental study considering adversarial active learning and an investigation of the efficacy of a mixed sample selection strategy for combating an adversary who attempts to disrupt the classifier learning.