Adversarial Robustness in Unsupervised Machine Learning: A Systematic Review
It provides a model for understanding attack properties to guide future research, addressing robustness issues for practitioners using unsupervised learning, though it is incremental as a review.
This paper conducted a systematic review of 86 papers to assess adversarial robustness in unsupervised machine learning, finding that most research addresses privacy attacks with effective defenses, but many attacks lack general defensive measures.
As the adoption of machine learning models increases, ensuring robust models against adversarial attacks is increasingly important. With unsupervised machine learning gaining more attention, ensuring it is robust against attacks is vital. This paper conducts a systematic literature review on the robustness of unsupervised learning, collecting 86 papers. Our results show that most research focuses on privacy attacks, which have effective defenses; however, many attacks lack effective and general defensive measures. Based on the results, we formulate a model on the properties of an attack on unsupervised learning, contributing to future research by providing a model to use.