This paper discusses the emerging field of adversarial machine learning, which focuses on developing effective techniques to counter adversarial attacks. The authors provide a taxonomy for classifying attacks against online machine learning algorithms, discuss application-specific factors that limit an adversary's capabilities, introduce models for modeling an adversary's capabilities, explore the limits of an adversary's knowledge, and examine vulnerabilities in machine learning algorithms. They also discuss countermeasures against attacks, the evasion challenge, and privacy-preserving learning techniques. The paper includes case studies on spam detection and network anomaly detection to illustrate the effectiveness of causative and exploratory attacks. The authors emphasize the importance of understanding the adversary's capabilities and limitations, as well as the assumptions made by the learning algorithms, to design robust and secure machine learning systems.This paper discusses the emerging field of adversarial machine learning, which focuses on developing effective techniques to counter adversarial attacks. The authors provide a taxonomy for classifying attacks against online machine learning algorithms, discuss application-specific factors that limit an adversary's capabilities, introduce models for modeling an adversary's capabilities, explore the limits of an adversary's knowledge, and examine vulnerabilities in machine learning algorithms. They also discuss countermeasures against attacks, the evasion challenge, and privacy-preserving learning techniques. The paper includes case studies on spam detection and network anomaly detection to illustrate the effectiveness of causative and exploratory attacks. The authors emphasize the importance of understanding the adversary's capabilities and limitations, as well as the assumptions made by the learning algorithms, to design robust and secure machine learning systems.