Artificial Intelligence is reshaping industries, but it introduces unique and evolving security risks. This course provides a foundational understanding of AI security, beginning with core concepts like vulnerabilities, threats, and risks specific to AI systems. You'll explore adversarial examples, attacks across the AI lifecycle, and how model behavior can be manipulated during training and inference. The course also covers key regulatory frameworks, ethical principles for responsible AI development, and real-world case studies—highlighting both the technical and societal implications of AI misuse. By the end, you'll understand how to design, test, and maintain more secure and trustworthy AI systems.