LLM security encompasses the policies, techniques, and defenses used to protect large language models from adversarial attacks, data leakage, misuse, and unintended harmful behavior. Unlike traditional software security, LLMs introduce unique vulnerabilities rooted in their inability to distinguish instructions from data, their vast attack surface across training pipelines and inference APIs, and their potential to generate harmful, biased, or incorrect content. Key concerns span prompt injection (manipulating model behavior through crafted inputs), data poisoning (corrupting training datasets to embed backdoors), privacy leakage (extracting sensitive information from model outputs or training data), and overreliance on unchecked outputs that can propagate misinformation or enable automated abuse. Understanding these risks—and the layered defenses needed to mitigate them—is essential for deploying LLMs safely in production environments where they interact with sensitive data, external systems, and human users.