Guest Editorial: Introduction to the Special Section on Security and Privacy for AI Models and Applications

The papers in this special section focus on security and privacy for artificial intelligence (AI) models and applications. AI is constantly changing our lives and has been applied to broad areas. When AI algorithms play a crucial role in bringing too much convenience to our society, they are also vulnerable to attacks. AI systems hacked by attackers may lead to incorrect classifications, property loss, and bad decision-making. The privacy issues of AI have also received more and more attention. Data used by AI models may reveal personal privacy, such as our consumption habits, medical information, and online transactions. Given AI models’ increased use in safety-critical and security applications, it is essential to ensure that such algorithms are robust to malicious adversaries and privacy preserved.