A Review of Security and Privacy in AI-managed Internet of Things Networks

Abstract

The Internet of Things (IoT) connects large numbers of devices that are often constrained, long-lived, and weakly secured, which makes IoT networks an attractive target for attackers. As artificial intelligence (AI) is increasingly used to manage these networks, the security picture changes in two ways at once. On one hand, machine learning and, more recently, agentic AI provide stronger tools for detecting and responding to threats. On the other hand, placing AI in control of the network introduces new risks of its own. In this review, the security and privacy of AI-managed IoT networks are examined from both directions. The main IoT threats are summarized, including botnets such as Mirai and the exploitation of known device vulnerabilities. The use of machine learning for intrusion detection is then reviewed, followed by the emerging use of large language model (LLM) based and agentic systems for autonomous defense and management. The new risks that arise when AI is given control, such as model manipulation, unreliable autonomous action, and an enlarged attack surface, are discussed, together with the privacy concerns raised by the large volumes of data these systems collect. Open challenges are identified, and directions for safer AI-managed IoT are suggested. A balanced view of both the promise and the hazards of managing IoT networks with AI is intended to be provided for practitioners and researchers.