A Comprehensive Analysis of Poisoning Attack and Defence Strategies in Machine Learning Techniques

Machine learning (ML) models have achieved remarkable success in various domains making them indispensable tools for critical applications. However, their susceptibility to adversarial attacks, particularly poisoning attacks, has raised serious concerns about their security and robustness. This review study aims to provide a complete analysis of poisoning attacks and defense strategies in ML techniques. We explore the various poisoning attack strategies, their potential impact on model performance, and examine the existing defense mechanisms to mitigate these threats. By shedding light on the latest advancements and challenges in this field, this study aims to guide researchers and practitioners towards building more secure and reliable machine learning models.