Not too long ago, AI security used to mean the research and practice of how AI can empower cybersecurity, that is, AI for security. Ever since Ian Goodfellow and his team popularized adversarial attacks on machine learning, security for AI became an important concern and also part of AI security. It is imperative to understand the threats to machine learning products and avoid common pitfalls in AI product development. This article is addressed to developers, designers, managers and researchers of AI software products.

翻译：不久之前，AI安全还曾指AI如何赋能网络安全的研究与实践，即AI赋能安全。自伊恩·古德费洛及其团队推广机器学习对抗性攻击以来，AI自身安全便成为重要关切，亦构成AI安全的一部分。理解机器学习产品面临的威胁、规避AI产品开发中的常见陷阱至关重要。本文面向AI软件产品的开发者、设计师、管理者及研究人员。