This paper provides an overview of emerging techniques for IP traffic classification using Machine Learning (ML). It discusses the motivation and context for applying ML to IP traffic classification, reviews 18 significant works from 2004 to early 2007, and critiques their contributions. The paper categorizes these works based on their ML strategies and primary contributions. Key requirements for operational IP networks are discussed, along with open issues and challenges in the field. The paper also highlights the limitations of traditional packet inspection methods and introduces statistical traffic properties as a new approach for classification. ML techniques, including supervised and unsupervised learning, are explained, and their application in IP traffic classification is detailed. The paper concludes with a discussion of the challenges and future directions in ML-based IP traffic classification.This paper provides an overview of emerging techniques for IP traffic classification using Machine Learning (ML). It discusses the motivation and context for applying ML to IP traffic classification, reviews 18 significant works from 2004 to early 2007, and critiques their contributions. The paper categorizes these works based on their ML strategies and primary contributions. Key requirements for operational IP networks are discussed, along with open issues and challenges in the field. The paper also highlights the limitations of traditional packet inspection methods and introduces statistical traffic properties as a new approach for classification. ML techniques, including supervised and unsupervised learning, are explained, and their application in IP traffic classification is detailed. The paper concludes with a discussion of the challenges and future directions in ML-based IP traffic classification.