A Survey on Poisoning Attacks Against Supervised Machine Learning

TL;DR

This survey reviews poisoning attacks on supervised machine learning, categorizing existing research, analyzing methodologies, and highlighting future directions to improve security and robustness.

Contribution

It provides a comprehensive taxonomy, detailed summaries, and critical analysis of existing poisoning attack studies, along with future research directions.

Findings

Taxonomy of poisoning attack methods

Comparison of methodologies and limitations

Identification of open research questions

Abstract

With the rise of artificial intelligence and machine learning in modern computing, one of the major concerns regarding such techniques is to provide privacy and security against adversaries. We present this survey paper to cover the most representative papers in poisoning attacks against supervised machine learning models. We first provide a taxonomy to categorize existing studies and then present detailed summaries for selected papers. We summarize and compare the methodology and limitations of existing literature. We conclude this paper with potential improvements and future directions to further exploit and prevent poisoning attacks on supervised models. We propose several unanswered research questions to encourage and inspire researchers for future work.