Intellicise Wireless Networks Meet Agentic AI: A Security and Privacy Perspective

TL;DR

This paper analyses the unique advantages that Agentic AI introduces to intellicise wireless networks and proposes a structured taxonomy for Agentic AI-enhanced secure intellicise wireless networks, and identifies emerging security and privacy challenges introduced by Agentic AI.

Abstract

Intellicise (Intelligent and Concise) wireless network is the main direction of the evolution of future mobile communication systems, a perspective now widely acknowledged across academia and industry. As a key technology within it, Agentic AI has garnered growing attention due to its advanced cognitive capabilities, enabled through continuous perception-memory-reasoning-action cycles. This paper first analyses the unique advantages that Agentic AI introduces to intellicise wireless networks. We then propose a structured taxonomy for Agentic AI-enhanced secure intellicise wireless networks. Building on this framework, we identify emerging security and privacy challenges introduced by Agentic AI and summarize targeted strategies to address these vulnerabilities. A case study further demonstrates Agentic AI's efficacy in defending against intelligent eavesdropping attacks. Finally, we outline key open research directions to guide future exploration in this field.

Figures (4)

• Figure 1: Overview of Agentic AI-enhanced Intellicise Wireless Networks, where Part (A) denotes the intellicise wirreless network, Part (C) denotes the workflow of Agentic AI, and Part (B) denotes three aspects of interplay between intellicise wireless networks and Agentic AI.
• Figure 2: Illustration of Agentic AI-enhanced secure intellicise wireless networks, where the italic text is the title of the corresponding article. Part (A) denotes Agentic AI for secure intellicise signal processing, Part (B) denotes Agentic AI for secure intellicise information transmission, and Part (C) denotes Agentic AI for secure intellicise network organization.
• Figure 3: Illustration of the presented Agentic AI-based semantic steganography communication scheme, where Part (A) represents the perception stage for perceiving secure transmission requirements and multi-modal semantic source information; Part (B) represents the memory stage for semantic model sharing and updating; Part (C) represents the reasoning stage for key generation and digital token setting; and Part (D) represents the action stage for the implementation of the semantic steganography strategy and optional semantic enhancement.
• Figure 4: Simulation results of the case study. We select the Stable Diffusion version 1.5 as the conditional diffusion model and employ the EDICT as the sampling algorithm. Both the forward and reverse processes are configured to include 50 steps. The SwinJSCC architecture is employed as the trained semantic encoder and decoder.